Search

Test Time Adaptation (TTA) has emerged as a practical solution to mitigate the performance degradation of Deep Neural Networks (DNNs) in the presence of corruption/ noise affecting inputs. Existing approaches in TTA continuously adapt the DNN, leading to excessive resource consumption and performance degradation due to accumulation of error stemming from lack of supervision. In this work, we propose Domain-Aware Real-Time Dynamic Adaptation (DARDA) to address such issues. Our key approach is to proactively learn latent representations of some corruption types, each one associated with a sub-network state tailored to correctly classify inputs affected by that corruption. After deployment, DARDA adapts the DNN to previously unseen corruptions in an unsupervised fashion by (i) estimating the latent representation of the ongoing corruption; (ii) selecting the sub-network whose associated corruption is the closest in the latent space to the ongoing corruption; and (iii) adapting DNN state, so that its representation matches the ongoing corruption. This way, DARDA is more resource efficient and can swiftly adapt to new distributions caused by different corruptions without requiring a large variety of input data. Through experiments with two popular mobile edge devices - Raspberry Pi and NVIDIA Jetson Nano - we show that DARDA reduces energy consumption and average cache memory footprint respectively by 1.74x and 2.64x with respect to the state of the art, while increasing the performance by 10.4%, 5.7% and 4.4% on CIFAR-10, CIFAR-100 and TinyImagenet.

Scientific edge computing increasingly relies on hardware-accelerated neural networks to implement complex, near-sensor processing at extremely high throughputs and low latencies. Existing frameworks like HLS4ML are effective for smaller models, but struggle with larger, modern neural networks due to their requirement of spatially implementing the neural network layers and storing all weights in on-chip memory. CGRA4ML is an open-source, modular framework designed to bridge the gap between neural network model complexity and extreme performance requirements. CGRA4ML extends the capabilities of HLS4ML by allowing off-chip data storage and supporting a broader range of neural network architectures, including models like ResNet, PointNet, and transformers. Unlike HLS4ML, CGRA4ML generates SystemVerilog RTL, making it more suitable for targeting ASIC and FPGA design flows. We demonstrate the effectiveness of our framework by implementing and scaling larger models that were previously unattainable with HLS4ML, showcasing its adaptability and efficiency in handling complex computations. CGRA4ML also introduces an extensive verification framework, with a generated runtime firmware that enables its integration into different SoC platforms. CGRA4ML's minimal and modular infrastructure of Python API, SystemVerilog hardware, Tcl toolflows, and C runtime, facilitates easy integration and experimentation, allowing scientists to focus on innovation rather than the intricacies of hardware design and optimization.

In order to deploy deep neural networks (DNNs) in high-stakes scenarios, it is imperative that DNNs provide inference robust to external perturbations - both intentional and unintentional. Although the resilience of DNNs to intentional and unintentional perturbations has been widely investigated, a unified vision of these inherently intertwined problem domains is still missing. In this work, we fill this gap by providing a survey of the state of the art and highlighting the similarities of the proposed approaches.We also analyze the research challenges that need to be addressed to deploy resilient and secure DNNs. As there has not been any such survey connecting the resilience of DNNs to intentional and unintentional perturbations, we believe this work can help advance the frontier in both domains by enabling the exchange of ideas between the two communities.

The deployment of a growing number of devices in Internet of Things (IoT) networks implies that uninterrupted and seamless adaptation of wireless communication parameters (e.g., carrier frequency, bandwidth and modulation) will become essential. To utilize wireless devices capable of switching several communication parameters requires real-time self-optimizations at the radio frequency integrated circuit (RFIC) level based on system level performance metrics during the processing of complex modulated signals. This article introduces a novel design verification approach for reconfigurable RFICs based on end-to-end wireless system-level performance metrics while operating in a dynamically changing communication environment. In contrast to prior work, this framework includes two modules that simulate a wireless channel and decode waveforms. These are connected to circuit-level modules that capture device- and circuit-level non-idealities of RFICs for design validation and optimization, such as transistor noises, intermodulation/harmonic distortions, and memory effects from parasitic capacitances. We demonstrate this framework with a receiver (RX) consisting of a reconfigurable complementary metal-oxide semiconductor (CMOS) low-noise amplifier (LNA) designed at the transistor level, a behavioral model of a mixer, and an ideal filter model. The seamless integration between system-level wireless models with circuit-level and behavioral models (such as VerilogA-based models) for RFIC blocks enables to preemptively evaluate circuit and system designs, and to optimize for different communication scenarios with adaptive circuits having extensive tuning ranges. An exemplary case study is presented, in which simulation results reveal that the LNA power consumption can be reduced up to 16x depending on system-level requirements., Comment: Accepted, 5 figures, 1 table. To be included in Proc. IEEE DySPAN 2024

Distributed deep neural networks (DNNs) have emerged as a key technique to reduce communication overhead without sacrificing performance in edge computing systems. Recently, entropy coding has been introduced to further reduce the communication overhead. The key idea is to train the distributed DNN jointly with an entropy model, which is used as side information during inference time to adaptively encode latent representations into bit streams with variable length. To the best of our knowledge, the resilience of entropy models is yet to be investigated. As such, in this paper we formulate and investigate the resilience of entropy models to intentional interference (e.g., adversarial attacks) and unintentional interference (e.g., weather changes and motion blur). Through an extensive experimental campaign with 3 different DNN architectures, 2 entropy models and 4 rate-distortion trade-off factors, we demonstrate that the entropy attacks can increase the communication overhead by up to 95%. By separating compression features in frequency and spatial domain, we propose a new defense mechanism that can reduce the transmission overhead of the attacked input by about 9% compared to unperturbed data, with only about 2% accuracy loss. Importantly, the proposed defense mechanism is a standalone approach which can be applied in conjunction with approaches such as adversarial training to further improve robustness. Code will be shared for reproducibility., Comment: accepted at ECCV 2024

Emerging mobile virtual reality (VR) systems will require to continuously perform complex computer vision tasks on ultra-high-resolution video frames through the execution of deep neural networks (DNNs)-based algorithms. Since state-of-the-art DNNs require computational power that is excessive for mobile devices, techniques based on wireless edge computing (WEC) have been recently proposed. However, existing WEC methods require the transmission and processing of a high amount of video data which may ultimately saturate the wireless link. In this paper, we propose a novel Sensing-Assisted Wireless Edge Computing (SAWEC) paradigm to address this issue. SAWEC leverages knowledge about the physical environment to reduce the end-to-end latency and overall computational burden by transmitting to the edge server only the relevant data for the delivery of the service. Our intuition is that the transmission of the portion of the video frames where there are no changes with respect to previous frames can be avoided. Specifically, we leverage wireless sensing techniques to estimate the location of objects in the environment and obtain insights about the environment dynamics. Hence, only the part of the frames where any environmental change is detected is transmitted and processed. We evaluated SAWEC by using a 10K 360$^{\circ}$ with a Wi-Fi 6 sensing system operating at 160 MHz and performing localization and tracking. We considered instance segmentation and object detection as benchmarking tasks for performance evaluation. We carried out experiments in an anechoic chamber and an entrance hall with two human subjects in six different setups. Experimental results show that SAWEC reduces both the channel occupation and end-to-end latency by more than 90% while improving the instance segmentation and object detection performance with respect to state-of-the-art WEC approaches., Comment: Submitted to ACM for possible publication

Integrated Sensing and Communication (ISAC) has been identified as a pillar usage scenario for the impending 6G era. Bi-static sensing, a major type of sensing in ISAC, is promising to expedite ISAC in the near future, as it requires minimal changes to the existing network infrastructure. However, a critical challenge for bi-static sensing is clock asynchronism due to the use of different clocks at far-separated transmitters and receivers. This causes the received signal to be affected by time-varying random phase offsets, severely degrading, or even failing, direct sensing. Hence, to effectively enable ISAC, considerable research has been directed toward addressing the clock asynchronism issue in bi-static sensing. This paper provides an overview of the issue and existing techniques developed in an ISAC background. Based on the review and comparison, we also draw insights into the future research directions and open problems, aiming to nurture the maturation of bi-static sensing in ISAC., Comment: 20 pages, 6 figures, 1 table

Spectrum has become an extremely scarce and congested resource. As a consequence, spectrum sensing enables the coexistence of different wireless technologies in shared spectrum bands. Most existing work requires spectrograms to classify signals. Ultimately, this implies that images need to be continuously created from I/Q samples, thus creating unacceptable latency for real-time operations. In addition, spectrogram-based approaches do not achieve sufficient granularity level as they are based on object detection performed on pixels and are based on rectangular bounding boxes. For this reason, we propose a completely novel approach based on semantic spectrum segmentation, where multiple signals are simultaneously classified and localized in both time and frequency at the I/Q level. Conversely from the state-of-the-art computer vision algorithm, we add non-local blocks to combine the spatial features of signals, and thus achieve better performance. In addition, we propose a novel data generation approach where a limited set of easy-to-collect real-world wireless signals are ``stitched together'' to generate large-scale, wideband, and diverse datasets. Experimental results obtained on multiple testbeds (including the Arena testbed) using multiple antennas, multiple sampling frequencies, and multiple radios over the course of 3 days show that our approach classifies and localizes signals with a mean intersection over union (IOU) of 96.70% across 5 wireless protocols while performing in real-time with a latency of 2.6 ms. Moreover, we demonstrate that our approach based on non-local blocks achieves 7% more accuracy when segmenting the most challenging signals with respect to the state-of-the-art U-Net algorithm. We will release our 17 GB dataset and code.

Ensuring predictability in modern real-time Systems-on-Chip (SoCs) is an increasingly critical concern for many application domains such as automotive, robotics, and industrial automation. An effective approach involves the modeling and development of hardware components, such as interconnects and shared memory resources, to evaluate or enforce their deterministic behavior. Unfortunately, these IPs are often closed-source, and these studies are limited to the single modules that must later be integrated with third-party IPs in more complex SoCs, hindering the precision and scope of modeling and compromising the overall predictability. With the coming-of-age of open-source instruction set architectures (RISC-V) and hardware, major opportunities for changing this status quo are emerging. This study introduces an innovative methodology for modeling and analyzing State-of-the-Art (SoA) open-source SoCs for low-power cyber-physical systems. Our approach models and analyzes the entire set of open-source IPs within these SoCs and then provides a comprehensive analysis of the entire architecture. We validate this methodology on a sample heterogenous low-power RISC-V architecture through RTL simulation and FPGA implementation, minimizing pessimism in bounding the service time of transactions crossing the architecture between 28% and 1%, which is considerably lower when compared to similar SoA works.

The increasing demand for heterogeneous functionality in the automotive industry and the evolution of chip manufacturing processes have led to the transition from federated to integrated critical real-time embedded systems (CRTESs). This leads to higher integration challenges of conventional timing predictability techniques due to access contention on shared resources, which can be resolved by providing system-level observability and controllability in hardware. We focus on the interconnect as a shared resource and propose AXI-REALM, a lightweight, modular, and technology-independent real-time extension to industry-standard AXI4 interconnects, available open-source. AXI-REALM uses a credit-based mechanism to distribute and control the bandwidth in a multi-subordinate system on periodic time windows, proactively prevents denial of service from malicious actors in the system, and tracks each manager's access and interference statistics for optimal budget and period selection. We provide detailed performance and implementation cost assessment in a 12nm node and an end-to-end functional case study implementing AXI-REALM into an open-source Linux-capable RISC-V SoC. In a system with a general-purpose core and a hardware accelerator's DMA engine causing interference on the interconnect, AXI-REALM achieves fair bandwidth distribution among managers, allowing the core to recover 68.2 % of its performance compared to the case without contention. Moreover, near-ideal performance (above 95 %) can be achieved by distributing the available bandwidth in favor of the core, improving the worst-case memory access latency from 264 to below eight cycles. Our approach minimizes buffering compared to other solutions and introduces only 2.45 % area overhead compared to the original SoC., Comment: 6 pages, 6 figures, accepted as a regular paper at DATE24

Modern IEEE 802.11 (Wi-Fi) networks extensively rely on multiple-input multiple-output (MIMO) to significantly improve throughput. To correctly beamform MIMO transmissions, the access point needs to frequently acquire a beamforming matrix (BM) from each connected station. However, the size of the matrix grows with the number of antennas and subcarriers, resulting in an increasing amount of airtime overhead and computational load at the station. Conventional approaches come with either excessive computational load or loss of beamforming precision. For this reason, we propose SplitBeam, a new framework where we train a split deep neural network (DNN) to directly output the BM given the channel state information (CSI) matrix as input. We formulate and solve a bottleneck optimization problem (BOP) to keep computation, airtime overhead, and bit error rate (BER) below application requirements. We perform extensive experimental CSI collection with off-the-shelf Wi-Fi devices in two distinct environments and compare the performance of SplitBeam with the standard IEEE 802.11 algorithm for BM feedback and the state-of-the-art DNN-based approach LB-SciFi. Our experimental results show that SplitBeam reduces the beamforming feedback size and computational complexity by respectively up to 81% and 84% while maintaining BER within about 10^-3 of existing approaches. We also implement the SplitBeam DNNs on FPGA hardware to estimate the end-to-end BM reporting delay, and show that the latter is less than 10 milliseconds in the most complex scenario, which is the target channel sounding frequency in realistic multi-user MIMO scenarios., Comment: Presented at the 43rd IEEE International Conference on Distributed Computing Systems (ICDCS 2023)

Deep neural networks (DNN) usually come with a significant computational burden. While approaches such as structured pruning and mobile-specific DNNs have been proposed, they incur drastic accuracy loss. In this paper we leverage the intrinsic redundancy in latent representations to reduce the computational load with limited loss in performance. We show that semantically similar inputs share many filters, especially in the earlier layers. Thus, semantically similar classes can be clustered to create cluster-specific subgraphs. To this end, we propose a new framework called Semantic Inference (SINF). In short, SINF (i) identifies the semantic cluster the object belongs to using a small additional classifier and (ii) executes the subgraph extracted from the base DNN related to that semantic cluster for inference. To extract each cluster-specific subgraph, we propose a new approach named Discriminative Capability Score (DCS) that finds the subgraph with the capability to discriminate among the members of a specific semantic cluster. DCS is independent from SINF and can be applied to any DNN. We benchmark the performance of DCS on the VGG16, VGG19, and ResNet50 DNNs trained on the CIFAR100 dataset against 6 state-of-the-art pruning approaches. Our results show that (i) SINF reduces the inference time of VGG19, VGG16, and ResNet50 respectively by up to 35%, 29% and 15% with only 0.17%, 3.75%, and 6.75% accuracy loss (ii) DCS achieves respectively up to 3.65%, 4.25%, and 2.36% better accuracy with VGG16, VGG19, and ResNet50 with respect to existing discriminative scores (iii) when used as a pruning criterion, DCS achieves up to 8.13% accuracy gain with 5.82% less parameters than the existing state of the art work published at ICLR 2023 (iv) when considering per-cluster accuracy, SINF performs on average 5.73%, 8.38% and 6.36% better than the base VGG16, VGG19, and ResNet50., Comment: 14 pages, 6 figures, conference format

Distributed deep neural networks (DNNs) have been shown to reduce the computational burden of mobile devices and decrease the end-to-end inference latency in edge computing scenarios. While distributed DNNs have been studied, to the best of our knowledge the resilience of distributed DNNs to adversarial action still remains an open problem. In this paper, we fill the existing research gap by rigorously analyzing the robustness of distributed DNNs against adversarial action. We cast this problem in the context of information theory and introduce two new measurements for distortion and robustness. Our theoretical findings indicate that (i) assuming the same level of information distortion, latent features are always more robust than input representations; (ii) the adversarial robustness is jointly determined by the feature dimension and the generalization capability of the DNN. To test our theoretical findings, we perform extensive experimental analysis by considering 6 different DNN architectures, 6 different approaches for distributed DNN and 10 different adversarial attacks to the ImageNet-1K dataset. Our experimental results support our theoretical findings by showing that the compressed latent representations can reduce the success rate of adversarial attacks by 88% in the best case and by 57% on the average compared to attacks to the input space.

Recently, researchers have shown that the beamforming feedback angles (BFAs) used for Wi-Fi multiple-input multiple-output (MIMO) operations can be effectively leveraged as a proxy of the channel frequency response (CFR) for different purposes. Examples are passive human activity recognition and device fingerprinting. However, even though the BFAs report frames are sent in clear text, there is not yet a unified open-source tool to extract and decode the BFAs from the frames. To fill this gap, we developed Wi-BFI, the first tool that allows retrieving Wi-Fi BFAs and reconstructing the beamforming feedback information (BFI) - a compressed representation of the CFR - from the BFAs frames captured over the air. The tool supports BFAs extraction within both IEEE 802.11ac and 802.11ax networks operating on radio channels with 160/80/40/20 MHz bandwidth. Both multi-user and single-user MIMO feedback can be decoded through Wi-BFI. The tool supports real-time and offline extraction and storage of BFAs and BFI. The real-time mode also includes a visual representation of the channel state that continuously updates based on the collected data. Wi-BFI code is open source and the tool is also available as a pip package., Comment: To be presented at ACM WiNTECH, Madrid, Spain, October 6, 2023

Recent advances in Wi-Fi sensing have ushered in a plethora of pervasive applications in home surveillance, remote healthcare, road safety, and home entertainment, among others. Most of the existing works are limited to the activity classification of a single human subject at a given time. Conversely, a more realistic scenario is to achieve simultaneous, multi-subject activity classification. The first key challenge in that context is that the number of classes grows exponentially with the number of subjects and activities. Moreover, it is known that Wi-Fi sensing systems struggle to adapt to new environments and subjects. To address both issues, we propose SiMWiSense, the first framework for simultaneous multi-subject activity classification based on Wi-Fi that generalizes to multiple environments and subjects. We address the scalability issue by using the Channel State Information (CSI) computed from the device positioned closest to the subject. We experimentally prove this intuition by confirming that the best accuracy is experienced when the CSI computed by the transceiver positioned closest to the subject is used for classification. To address the generalization issue, we develop a brand-new few-shot learning algorithm named Feature Reusable Embedding Learning (FREL). Through an extensive data collection campaign in 3 different environments and 3 subjects performing 20 different activities simultaneously, we demonstrate that SiMWiSense achieves classification accuracy of up to 97%, while FREL improves the accuracy by 85% in comparison to a traditional Convolutional Neural Network (CNN) and up to 20% when compared to the state-of-the-art few-shot embedding learning (FSEL), by using only 15 seconds of additional data for each class. For reproducibility purposes, we share our 1TB dataset and code repository., Comment: This work has been accepted for publication in IEEE WoWMoM 2023

In this paper, we propose BeamSense, a completely novel approach to implement standard-compliant Wi-Fi sensing applications. Wi-Fi sensing enables game-changing applications in remote healthcare, home entertainment, and home surveillance, among others. However, existing work leverages the manual extraction of channel state information (CSI) from Wi-Fi chips to classify activities, which is not supported by the Wi-Fi standard and hence requires the usage of specialized equipment. On the contrary, BeamSense leverages the standard-compliant beamforming feedback information (BFI) to characterize the propagation environment. Conversely from CSI, the BFI (i) can be easily recorded without any firmware modification, and (ii) captures the multiple channels between the access point and the stations, thus providing much better sensitivity. BeamSense includes a novel cross-domain few-shot learning (FSL) algorithm to handle unseen environments and subjects with few additional data points. We evaluate BeamSense through an extensive data collection campaign with three subjects performing twenty different activities in three different environments. We show that our BFI-based approach achieves about 10% more accuracy when compared to CSI-based prior work, while our FSL strategy improves accuracy by up to 30% and 80% when compared with state-of-the-art cross-domain algorithms., Comment: This work has been submitted to the IEEE for possible publication

Thanks to the ubiquitous deployment of Wi-Fi hotspots, channel state information (CSI)-based Wi-Fi sensing can unleash game-changing applications in many fields, such as healthcare, security, and entertainment. However, despite one decade of active research on Wi-Fi sensing, most existing work only considers legacy IEEE 802.11n devices, often in particular and strictly-controlled environments. Worse yet, there is a fundamental lack of understanding of the impact on CSI-based sensing of modern Wi-Fi features, such as 160-MHz bandwidth, multiple-input multiple-output (MIMO) transmissions, and increased spectral resolution in IEEE 802.11ax (Wi-Fi 6). This work aims to shed light on the impact of Wi-Fi 6 features on the sensing performance and to create a benchmark for future research on Wi-Fi sensing. To this end, we perform an extensive CSI data collection campaign involving 3 individuals, 3 environments, and 12 activities, using Wi-Fi 6 signals. An anonymized ground truth obtained through video recording accompanies our 80-GB dataset, which contains almost two hours of CSI data from three collectors. We leverage our dataset to dissect the performance of a state-of-the-art sensing framework across different environments and individuals. Our key findings suggest that (i) MIMO transmissions and higher spectral resolution might be more beneficial than larger bandwidth for sensing applications; (ii) there is a pressing need to standardize research on Wi-Fi sensing because the path towards a truly environment-independent framework is still uncertain. To ease the experiments' replicability and address the current lack of Wi-Fi 6 CSI datasets, we release our 80-GB dataset to the community., Comment: 10 pages, 13 figures, accepted for publication in Proceedings of IEEE PerCom 2023

To perform advanced surveillance, Unmanned Aerial Vehicles (UAVs) require the execution of edge-assisted computer vision (CV) tasks. In multi-hop UAV networks, the successful transmission of these tasks to the edge is severely challenged due to severe bandwidth constraints. For this reason, we propose a novel A$^2$-UAV framework to optimize the number of correctly executed tasks at the edge. In stark contrast with existing art, we take an application-aware approach and formulate a novel pplication-Aware Task Planning Problem (A$^2$-TPP) that takes into account (i) the relationship between deep neural network (DNN) accuracy and image compression for the classes of interest based on the available dataset, (ii) the target positions, (iii) the current energy/position of the UAVs to optimize routing, data pre-processing and target assignment for each UAV. We demonstrate A$^2$-TPP is NP-Hard and propose a polynomial-time algorithm to solve it efficiently. We extensively evaluate A$^2$-UAV through real-world experiments with a testbed composed by four DJI Mavic Air 2 UAVs. We consider state-of-the-art image classification tasks with four different DNN models (i.e., DenseNet, ResNet152, ResNet50 and MobileNet-V2) and object detection tasks using YoloV4 trained on the ImageNet dataset. Results show that A$^2$-UAV attains on average around 38% more accomplished tasks than the state-of-the-art, with 400% more accomplished tasks when the number of targets increases significantly. To allow full reproducibility, we pledge to share datasets and code with the research community., Comment: Accepted to INFOCOM 2023

As Wi-Fi becomes ubiquitous in public and private spaces, it becomes natural to leverage its intrinsic ability to sense the surrounding environment to implement groundbreaking wireless sensing applications such as human presence detection, activity recognition, and object tracking. For this reason, the IEEE 802.11bf Task Group is defining the appropriate modifications to existing Wi-Fi standards to enhance sensing capabilities through 802.11-compliant devices. However, the new standard is expected to leave the specific sensing algorithms open to implementation. To fill this gap, this article explores the practical implications of integrating sensing into Wi-Fi networks. We provide an overview of the physical and medium access control layers sensing enablers, together with the application layer perspective. We analyze the impact of communication parameters on sensing performance and detail the main research challenges. To make our evaluation replicable, we pledge to release all of our dataset and code to the community., Comment: Accepted for publication in IEEE Communications Magazine

5G and beyond cellular networks (NextG) will support the continuous execution of resource-expensive edge-assisted deep learning (DL) tasks. To this end, Radio Access Network (RAN) resources will need to be carefully "sliced" to satisfy heterogeneous application requirements while minimizing RAN usage. Existing slicing frameworks treat each DL task as equal and inflexibly define the resources to assign to each task, which leads to sub-optimal performance. In this paper, we propose SEM-O-RAN, the first semantic and flexible slicing framework for NextG Open RANs. Our key intuition is that different DL classifiers can tolerate different levels of image compression, due to the semantic nature of the target classes. Therefore, compression can be semantically applied so that the networking load can be minimized. Moreover, flexibility allows SEM-O-RAN to consider multiple edge allocations leading to the same task-related performance, which significantly improves system-wide performance as more tasks can be allocated. First, we mathematically formulate the Semantic Flexible Edge Slicing Problem (SF-ESP), demonstrate that it is NP-hard, and provide an approximation algorithm to solve it efficiently. Then, we evaluate the performance of SEM-O-RAN through extensive numerical analysis with state-of-the-art multi-object detection (YOLOX) and image segmentation (BiSeNet V2), as well as real-world experiments on the Colosseum testbed. Our results show that SEM-O-RAN improves the number of allocated tasks by up to 169% with respect to the state of the art., Comment: Accepted in IEEE INFOCOM 2023

Next-generation wireless networks will leverage the spectrum above 100 GHz to enable ultra-high data rate communications over multi-GHz-wide bandwidths. The propagation environment at such high frequencies, however, introduces challenges throughout the whole protocol stack design, from physical layer signal processing to application design. Therefore, it is fundamental to develop a holistic understanding of the channel propagation and fading characteristics over realistic deployment scenarios and ultra-wide bands. In this paper, we conduct an extensive measurement campaign to evaluate the impact of weather conditions on a wireless link in the 130-150 GHz band through a channel sounding campaign with clear weather, rain, and snow in a typical urban backhaul scenario. We present a novel channel sounder design that captures signals with -82 dBm sensitivity and 20 GHz of bandwidth. We analyze link budget, capacity, as well as channel parameters such as the delay spread and the K-factor. Our experimental results indicate that in the considered context the adverse weather does not interrupt the link, but introduces some additional constraints (e.g., high delay spread and increase in path loss in snow conditions) that need to be accounted for in the design of reliable Sixth Generation (6G) communication links above 100 GHz., Comment: P. Sen, J. Hall, M. Polese, V. Petrov, D. Bodet, F. Restuccia, T. Melodia, J. M. Jornet. 2022. Terahertz Communications Can Work in Rain and Snow: Impact of Adverse Weather Conditions on Channels at 140 GHz. In 6th ACM Workshop on Millimeter-Wave and Terahertz Networks and Sensing Systems (mmNets'22), October 17, 2022, Sydney, NSW, Australia. ACM, New York, NY, USA, 6 pages

Many analytical models have been proposed for evaluating the performance of event-driven 802.15.4 Wireless Sensor Networks (WSNs), in Non-Beacon Enabled (NBE) mode. However, existing models do not provide accurate analysis of large-scale WSNs, due to tractability issues and/or simplifying assumptions. In this paper, we propose a new approach called Event Chains Computation (ECC) to model the unslotted CSMA/CA algorithm used for channel access in NBE mode. ECC relies on the idea that outcomes of the CSMA/CA algorithm can be represented as chains of events that subsequently occur in the network. Although ECC can generate all the possible outcomes, it only considers chains with a probability to occur greater than a pre-defined threshold to reduce complexity. Furthermore, ECC parallelizes the computation by managing different chains through different threads. Our results show that, by an appropriate threshold selection, the time to derive performance metrics can be drastically reduced, with negligible impact on accuracy. We also show that the computation time decreases almost linearly with the number of employed threads. We validate our model through simulations and testbed experiments, and use it to investigate the impact of different parameters on the WSN performance, in terms of delivery ratio, latency, and energy consumption.

We present DeepCSI, a novel approach to Wi-Fi radio fingerprinting (RFP) which leverages standard-compliant beamforming feedback matrices to authenticate MU-MIMO Wi-Fi devices on the move. By capturing unique imperfections in off-the-shelf radio circuitry, RFP techniques can identify wireless devices directly at the physical layer, allowing low-latency low-energy cryptography-free authentication. However, existing Wi-Fi RFP techniques are based on software-defined radio (SDRs), which may ultimately prevent their widespread adoption. Moreover, it is unclear whether existing strategies can work in the presence of MU-MIMO transmitters - a key technology in modern Wi-Fi standards. Conversely from prior work, DeepCSI does not require SDR technologies and can be run on any low-cost Wi-Fi device to authenticate MU-MIMO transmitters. Our key intuition is that imperfections in the transmitter's radio circuitry percolate onto the beamforming feedback matrix, and thus RFP can be performed without explicit channel state information (CSI) computation. DeepCSI is robust to inter-stream and inter-user interference being the beamforming feedback not affected by those phenomena. We extensively evaluate the performance of DeepCSI through a massive data collection campaign performed in the wild with off-the-shelf equipment, where 10 MU-MIMO Wi-Fi radios emit signals in different positions. Experimental results indicate that DeepCSI correctly identifies the transmitter with an accuracy of up to 98%. The identification accuracy remains above 82% when the device moves within the environment. To allow replicability and provide a performance benchmark, we pledge to share the 800 GB datasets - collected in static and, for the first time, dynamic conditions - and the code database with the community., Comment: To be presented at the 42nd IEEE International Conference on Distributed Computing Systems (ICDCS), Bologna, Italy, July 10-13, 2022

Today's radio access networks (RANs) are monolithic entities which often operate statically on a given set of parameters for the entirety of their operations. To implement realistic and effective spectrum sharing policies, RANs will need to seamlessly and intelligently change their operational parameters. In stark contrast with existing paradigms, the new O-RAN architectures for 5G-and-beyond networks (NextG) separate the logic that controls the RAN from its hardware substrate, allowing unprecedented real-time fine-grained control of RAN components. In this context, we propose the Channel-Aware Reactive Mechanism (ChARM), a data-driven O-RAN-compliant framework that allows (i) sensing the spectrum to infer the presence of interference and (ii) reacting in real time by switching the distributed unit (DU) and radio unit (RU) operational parameters according to a specified spectrum access policy. ChARM is based on neural networks operating directly on unprocessed I/Q waveforms to determine the current spectrum context. ChARM does not require any modification to the existing 3GPP standards. It is designed to operate within the O-RAN specifications, and can be used in conjunction with other spectrum sharing mechanisms (e.g., LTE-U, LTE-LAA or MulteFire). We demonstrate the performance of ChARM in the context of spectrum sharing among LTE and Wi-Fi in unlicensed bands, where a controller operating over a RAN Intelligent Controller (RIC) senses the spectrum and switches cell frequency to avoid Wi-Fi. We develop a prototype of ChARM using srsRAN, and leverage the Colosseum channel emulator to collect a large-scale waveform dataset to train our neural networks with. Experimental results show that ChARM achieves accuracy of up to 96% on Colosseum and 85% on an over-the-air testbed, demonstrating the capacity of ChARM to exploit the considered spectrum channels., Comment: 10 pages, accepted at IEEE INFOCOM 2022 IEEE Conference on Computer Communications, May 2022

Mobile devices increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) can be used with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which may make the reference outdated and degrade tracking quality. Herein, we propose to use edge computing in this context, and establish parallel OT (at the mobile device) and OD (at the edge server) processes that are resilient to large OD latency. We propose Katch-Up, a novel tracking mechanism that improves the system resilience to excessive OD delay. However, while Katch-Up significantly improves performance, it also increases the computing load of the mobile device. Hence, we design SmartDet, a low-complexity controller based on deep reinforcement learning (DRL) that learns controlling the trade-off between resource utilization and OD performance. SmartDet takes as input context-related information related to the current video content and the current network conditions to optimize frequency and type of OD offloading, as well as Katch-Up utilization. We extensively evaluate SmartDet on a real-world testbed composed of a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link. Experimental results show that SmartDet achieves an optimal balance between tracking performance - mean Average Recall (mAR) and resource usage. With respect to a baseline with full Katch-Upusage and maximum channel usage, we still increase mAR by 4% while using 50% less of the channel and 30% power resources associated with Katch-Up. With respect to a fixed strategy using minimal resources, we increase mAR by 20% while using Katch-Up on 1/3 of the frames.

Although mission-critical applications require the use of deep neural networks (DNNs), their continuous execution at mobile devices results in a significant increase in energy consumption. While edge offloading can decrease energy consumption, erratic patterns in channel quality, network and edge server load can lead to severe disruption of the system's key operations. An alternative approach, called split computing, generates compressed representations within the model (called "bottlenecks"), to reduce bandwidth usage and energy consumption. Prior work has proposed approaches that introduce additional layers, to the detriment of energy consumption and latency. For this reason, we propose a new framework called BottleFit, which, in addition to targeted DNN architecture modifications, includes a novel training strategy to achieve high accuracy even with strong compression rates. We apply BottleFit on cutting-edge DNN models in image classification, and show that BottleFit achieves 77.1% data compression with up to 0.6% accuracy loss on ImageNet dataset, while state of the art such as SPINN loses up to 6% in accuracy. We experimentally measure the power consumption and latency of an image classification application running on an NVIDIA Jetson Nano board (GPU-based) and a Raspberry PI board (GPU-less). We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w.r.t.) local computing and by 37% and 55% w.r.t. edge offloading. We also compare BottleFit with state-of-the-art autoencoders-based approaches, and show that (i) BottleFit reduces power consumption and execution time respectively by up to 54% and 44% on the Jetson and 40% and 62% on Raspberry PI; (ii) the size of the head model executed on the mobile device is 83 times smaller. We publish the code repository for reproducibility of the results in this study., Comment: Accepted to IEEE WoWMoM 2022. Code and models are available at https://github.com/yoshitomo-matsubara/bottlefit-split_computing

Thanks to the ubiquitousness of Wi-Fi access points and devices, Wi-Fi sensing enables transformative applications in remote health care, security, and surveillance. Existing work has explored the usage of machine learning on channel state information (CSI) computed from Wi-Fi packets to classify events of interest. However, most of these algorithms require a significant amount of data collection, as well as extensive computational power for additional CSI feature extraction. Moreover, the majority of these models suffer from poor accuracy when tested in a new/untrained environment. In this paper, we propose ReWiS, a novel framework for robust and environment-independent Wi-Fi sensing. The key innovation of ReWiS is to leverage few-shot learning (FSL) as the inference engine, which (i) reduces the need for extensive data collection and application-specific feature extraction; (ii) can rapidly generalize to new tasks by leveraging only a few new samples. We prototype ReWiS using off-the-shelf Wi-Fi equipment and showcase its performance by considering a compelling use case of human activity recognition. Thus, we perform an extensive data collection campaign in three different propagation environments with two human subjects. We evaluate the impact of each diversity component on the performance and compare ReWiS with a traditional convolutional neural network (CNN) approach. Experimental results show that ReWiS improves the performance by about 40% with respect to existing single-antenna low-resolution approaches. Moreover, when compared to a CNN-based approach, ReWiS shows a 35% more accuracy and less than 10% drop in accuracy when tested in different environments, while the CNN drops by more than 45%.

Next Generation (NextG) networks are expected to support demanding tactile internet applications such as augmented reality and connected autonomous vehicles. Whereas recent innovations bring the promise of larger link capacity, their sensitivity to the environment and erratic performance defy traditional model-based control rationales. Zero-touch data-driven approaches can improve the ability of the network to adapt to the current operating conditions. Tools such as reinforcement learning (RL) algorithms can build optimal control policy solely based on a history of observations. Specifically, deep RL (DRL), which uses a deep neural network (DNN) as a predictor, has been shown to achieve good performance even in complex environments and with high dimensional inputs. However, the training of DRL models require a large amount of data, which may limit its adaptability to ever-evolving statistics of the underlying environment. Moreover, wireless networks are inherently distributed systems, where centralized DRL approaches would require excessive data exchange, while fully distributed approaches may result in slower convergence rates and performance degradation. In this paper, to address these challenges, we propose a federated learning (FL) approach to DRL, which we refer to federated DRL (F-DRL), where base stations (BS) collaboratively train the embedded DNN by only sharing models' weights rather than training data. We evaluate two distinct versions of F-DRL, value and policy based, and show the superior performance they achieve compared to distributed and centralized DRL., Comment: 6pages

Colosseum is an open-access and publicly-available large-scale wireless testbed for experimental research via virtualized and softwarized waveforms and protocol stacks on a fully programmable, "white-box" platform. Through 256 state-of-the-art software-defined radios and a massive channel emulator core, Colosseum can model virtually any scenario, enabling the design, development and testing of solutions at scale in a variety of deployments and channel conditions. These Colosseum radio-frequency scenarios are reproduced through high-fidelity FPGA-based emulation with finite-impulse response filters. Filters model the taps of desired wireless channels and apply them to the signals generated by the radio nodes, faithfully mimicking the conditions of real-world wireless environments. In this paper, we introduce Colosseum as a testbed that is for the first time open to the research community. We describe the architecture of Colosseum and its experimentation and emulation capabilities. We then demonstrate the effectiveness of Colosseum for experimental research at scale through exemplary use cases including prevailing wireless technologies (e.g., cellular and Wi-Fi) in spectrum sharing and unmanned aerial vehicle scenarios. A roadmap for Colosseum future updates concludes the paper.

Modern systems on a chip (SoCs) utilize heterogeneous architectures where multiple IP cores have concurrent access to on-chip shared resources. In security-critical applications, IP cores have different privilege levels for accessing shared resources, which must be regulated by an access control system. AKER is a design and verification framework for SoC access control. AKER builds upon the Access Control Wrapper (ACW) -- a high performance and easy-to-integrate hardware module that dynamically manages access to shared resources. To build an SoC access control system, AKER distributes the ACWs throughout the SoC, wrapping controller IP cores, and configuring the ACWs to perform local access control. To ensure the access control system is functioning correctly and securely, AKER provides a property-driven security verification using MITRE common weakness enumerations. AKER verifies the SoC access control at the IP level to ensure the absence of bugs in the functionalities of the ACW module, at the firmware level to confirm the secure operation of the ACW when integrated with a hardware root-of-trust (HRoT), and at the system level to evaluate security threats due to the interactions among shared resources. The performance, resource usage, and security of access control systems implemented through AKER is experimentally evaluated on a Xilinx UltraScale+ programmable SoC, it is integrated with the OpenTitan hardware root-of-trust, and it is used to design an access control system for the OpenPULP multicore architecture.

Isadora is a methodology for creating information flow specifications of hardware designs. The methodology combines information flow tracking and specification mining to produce a set of information flow properties that are suitable for use during the security validation process, and which support a better understanding of the security posture of the design. Isadora is fully automated; the user provides only the design under consideration and a testbench and need not supply a threat model nor security specifications. We evaluate Isadora on a RISC-V processor plus two designs related to SoC access control. Isadora generates security properties that align with those suggested by the Common Weakness Enumerations (CWEs), and in the case of the SoC designs, align with the properties written manually by security experts., Comment: 10 pages, 4 figures, accepted at ASHES 2021

Millions of RFID tags are pervasively used all around the globe to inexpensively identify a wide variety of everyday-use objects. One of the key issues of RFID is that tags cannot use energy-hungry cryptography. For this reason, radio fingerprinting (RFP) is a compelling approach that leverages the unique imperfections in the tag's wireless circuitry to achieve large-scale RFID clone detection. Recent work, however, has unveiled that time-varying channel conditions can significantly decrease the accuracy of the RFP process. We propose the first large-scale investigation into RFP of RFID tags with dynamic channel conditions. Specifically, we perform a massive data collection campaign on a testbed composed by 200 off-the-shelf identical RFID tags and a software-defined radio (SDR) tag reader. We collect data with different tag-reader distances in an over-the-air configuration. To emulate implanted RFID tags, we also collect data with two different kinds of porcine meat inserted between the tag and the reader. We use this rich dataset to train and test several convolutional neural network (CNN)--based classifiers in a variety of channel conditions. Our investigation reveals that training and testing on different channel conditions drastically degrades the classifier's accuracy. For this reason, we propose a novel training framework based on federated machine learning (FML) and data augmentation (DAG) to boost the accuracy. Extensive experimental results indicate that (i) our FML approach improves accuracy by up to 48%; (ii) our DA approach improves the FML performance by up to 31%. To the best of our knowledge, this is the first paper experimentally demonstrating the efficacy of FML and DA on a large device population. We are sharing with the research community our fully-labeled 200-GB RFID waveform dataset, the entirety of our code and trained models.

Edge computing enables Mobile Autonomous Systems (MASs) to execute continuous streams of heavy-duty mission-critical processing tasks, such as real-time obstacle detection and navigation. However, in practical applications, erratic patterns in channel quality, network load, and edge server load can interrupt the task flow execution, which necessarily leads to severe disruption of the system's key operations. Existing work has mostly tackled the problem with reactive approaches, which cannot guarantee task-level reliability. Conversely, in this paper we focus on learning-based predictive edge computing to achieve self-resilient task offloading. By conducting a preliminary experimental evaluation, we show that there is no dominant feature that can predict the edge-MAS system reliability, which calls for an ensemble and selection of weaker features. To tackle the complexity of the problem, we propose SeReMAS, a data-driven optimization framework. We first mathematically formulate a Redundant Task Offloading Problem (RTOP), where a MAS may connect to multiple edge servers for redundancy, and needs to select which server(s) to transmit its computing tasks in order to maximize the probability of task execution while minimizing channel and edge resource utilization. We then create a predictor based on Deep Reinforcement Learning (DRL), which produces the optimum task assignment based on application-, network- and telemetry-based features. We prototype SeReMAS on a testbed composed by a drone, mounting a PixHawk flight controller, a Jetson Nano board, and three 802.11n WiFi interfaces. We extensively evaluate SeReMAS by considering an application where one drone offloads high-resolution images for real-time analysis to three edge servers on the ground. Experimental results show that SeReMAS improves task execution probability by $17\%$ with respect to existing reactive-based approaches., Comment: Corrected typo in title

Wi-Fi is among the most successful wireless technologies ever invented. As Wi-Fi becomes more and more present in public and private spaces, it becomes natural to leverage its ubiquitousness to implement groundbreaking wireless sensing applications such as human presence detection, activity recognition, and object tracking, just to name a few. This paper reports ongoing efforts by the IEEE 802.11bf Task Group (TGbf), which is defining the appropriate modifications to existing Wi-Fi standards to enhance sensing capabilities through 802.11-compliant waveforms. We summarize objectives and timeline of TGbf, and discuss some of the most interesting proposed technical features discussed so far. We also introduce a roadmap of research challenges pertaining to Wi-Fi sensing and its integration with future Wi-Fi technologies and emerging spectrum bands, hoping to elicit further activities by both the research community and TGbf.

Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud/edge servers may decrease the mobile device's computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple "exits" earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the trade-off between accuracy and delay can be tuned according to the current conditions or application demands. In this paper, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the paper by providing a set of compelling research challenges., Comment: Accepted to ACM Computing Surveys (CSUR)

Thanks to its capability of classifying complex phenomena without explicit modeling, deep learning (DL) has been demonstrated to be a key enabler of Wireless Signal Classification (WSC). Although DL can achieve a very high accuracy under certain conditions, recent research has unveiled that the wireless channel can disrupt the features learned by the DL model during training, thus drastically reducing the classification performance in real-world live settings. Since retraining classifiers is cumbersome after deployment, existing work has leveraged the usage of carefully-tailored Finite Impulse Response (FIR) filters that, when applied at the transmitter's side, can restore the features that are lost because of the the channel actions, i.e., waveform synthesis. However, these approaches compute FIRs using offline optimization strategies, which limits their efficacy in highly-dynamic channel settings. In this paper, we improve the state of the art by proposing Chares, a Deep Reinforcement Learning (DRL)-based framework for channel-resilient adaptive waveform synthesis. Chares adapts to new and unseen channel conditions by optimally computing through DRL the FIRs in real-time. Chares is a DRL agent whose architecture is-based upon the Twin Delayed Deep Deterministic Policy Gradients (TD3), which requires minimal feedback from the receiver and explores a continuous action space. Chares has been extensively evaluated on two well-known datasets. We have also evaluated the real-time latency of Chares with an implementation on field-programmable gate array (FPGA). Results show that Chares increases the accuracy up to 4.1x when no waveform synthesis is performed, by 1.9x with respect to existing work, and can compute new actions within 41us.

Fifth-generation (5G) systems will extensively employ radio access network (RAN) softwarization. This key innovation enables the instantiation of "virtual cellular networks" running on different slices of the shared physical infrastructure. In this paper, we propose the concept of Private Cellular Connectivity as a Service (PCCaaS), where infrastructure providers deploy covert network slices known only to a subset of users. We then present SteaLTE as the first realization of a PCCaaS-enabling system for cellular networks. At its core, SteaLTE utilizes wireless steganography to disguise data as noise to adversarial receivers. Differently from previous work, however, it takes a full-stack approach to steganography, contributing an LTE-compliant steganographic protocol stack for PCCaaS-based communications, and packet schedulers and operations to embed covert data streams on top of traditional cellular traffic (primary traffic). SteaLTE balances undetectability and performance by mimicking channel impairments so that covert data waveforms are almost indistinguishable from noise. We evaluate the performance of SteaLTE on an indoor LTE-compliant testbed under different traffic profiles, distance and mobility patterns. We further test it on the outdoor PAWR POWDER platform over long-range cellular links. Results show that in most experiments SteaLTE imposes little loss of primary traffic throughput in presence of covert data transmissions (< 6%), making it suitable for undetectable PCCaaS networking.

The use of the term blockchain is documented for disparate projects, from cryptocurrencies to applications for the Internet of Things (IoT), and many more. The concept of blockchain appears therefore blurred, as it is hard to believe that the same technology can empower applications that have extremely different requirements and exhibit dissimilar performance and security. This position paper elaborates on the theory of distributed systems to advance a clear definition of blockchain that allows us to clarify its role in the IoT. This definition inextricably binds together three elements that, as a whole, provide the blockchain with those unique features that distinguish it from other distributed ledger technologies: immutability, transparency and anonimity. We note however that immutability comes at the expense of remarkable resource consumption, transparency demands no confidentiality and anonymity prevents user identification and registration. This is in stark contrast to the requirements of most IoT applications that are made up of resource constrained devices, whose data need to be kept confidential and users to be clearly known. Building on the proposed definition, we derive new guidelines for selecting the proper distributed ledger technology depending on application requirements and trust models, identifying common pitfalls leading to improper applications of the blockchain. We finally indicate a feasible role of the blockchain for the IoT: myriads of local, IoT transactions can be aggregated off-chain and then be successfully recorded on an external blockchain as a means of public accountability when required.

Highly directional millimeter wave (mmWave) radios need to perform beam management to establish and maintain reliable links. To do so, existing solutions mostly rely on explicit coordination between the transmitter (TX) and the receiver (RX), which significantly reduces the airtime available for communication and further complicates the network protocol design. This paper advances the state of the art by presenting DeepBeam, a framework for beam management that does not require pilot sequences from the TX, nor any beam sweeping or synchronization from the RX. This is achieved by inferring (i) the Angle of Arrival (AoA) of the beam and (ii) the actual beam being used by the transmitter through waveform-level deep learning on ongoing transmissions between the TX to other receivers. In this way, the RX can associate Signal-to-Noise-Ratio (SNR) levels to beams without explicit coordination with the TX. This is possible because different beam patterns introduce different impairments to the waveform, which can be subsequently learned by a convolutional neural network (CNN). We conduct an extensive experimental data collection campaign where we collect more than 4 TB of mmWave waveforms with (i) 4 phased array antennas at 60.48 GHz, (ii) 2 codebooks containing 24 one-dimensional beams and 12 two-dimensional beams; (iii) 3 receiver gains; (iv) 3 different AoAs; (v) multiple TX and RX locations. Moreover, we collect waveform data with two custom-designed mmWave software-defined radios with fully-digital beamforming architectures at 58 GHz. Results show that DeepBeam (i) achieves accuracy of up to 96%, 84% and 77% with a 5-beam, 12-beam and 24-beam codebook, respectively; (ii) reduces latency by up to 7x with respect to the 5G NR initial beam sweep in a default configuration and with a 12-beam codebook. The waveform dataset and the full DeepBeam code repository are publicly available., Comment: 10 pages, 15 figures. Please cite it as M. Polese, F. Restuccia, and T. Melodia, "DeepBeam: Deep Waveform Learning for Coordination-Free Beam Management in mmWave Networks", Proc. of ACM Intl. Symp. on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (ACM MobiHoc), October 2021

Deep learning can be used to classify waveform characteristics (e.g., modulation) with accuracy levels that are hardly attainable with traditional techniques. Recent research has demonstrated that one of the most crucial challenges in wireless deep learning is to counteract the channel action, which may significantly alter the waveform features. The problem is further exacerbated by the fact that deep learning algorithms are hardly re-trainable in real time due to their sheer size. This paper proposes DeepFIR, a framework to counteract the channel action in wireless deep learning algorithms without retraining the underlying deep learning model. The key intuition is that through the application of a carefully-optimized digital finite input response filter (FIR) at the transmitter's side, we can apply tiny modifications to the waveform to strengthen its features according to the current channel conditions. We mathematically formulate the Waveform Optimization Problem (WOP) as the problem of finding the optimum FIR to be used on a waveform to improve the classifier's accuracy. We also propose a data-driven methodology to train the FIRs directly with dataset inputs. We extensively evaluate DeepFIR on a experimental testbed of 20 software-defined radios, as well as on two datasets made up by 500 ADS-B devices and by 500 WiFi devices and a 24-class modulation dataset. Experimental results show that our approach (i) increases the accuracy of the radio fingerprinting models by about 35%, 50% and 58%; (ii) decreases an adversary's accuracy by about 54% when trying to imitate other device's fingerprints by using their filters; (iii) achieves 27% improvement over the state of the art on a 100-device dataset; (iv) increases by 2x the accuracy of the modulation dataset., Comment: submitted to IEEE Transactions on Wireless Communications. arXiv admin note: substantial text overlap with arXiv:1904.07623

This paper advances the state of the art by proposing the first comprehensive analysis and experimental evaluation of adversarial learning attacks to wireless deep learning systems. We postulate a series of adversarial attacks, and formulate a Generalized Wireless Adversarial Machine Learning Problem (GWAP) where we analyze the combined effect of the wireless channel and the adversarial waveform on the efficacy of the attacks. We propose a new neural network architecture called FIRNet, which can be trained to "hack" a classifier based only on its output. We extensively evaluate the performance on (i) a 1,000-device radio fingerprinting dataset, and (ii) a 24-class modulation dataset. Results obtained with several channel conditions show that our algorithms can decrease the classifier accuracy up to 3x. We also experimentally evaluate FIRNet on a radio testbed, and show that our data-driven blackbox approach can confuse the classifier up to 97% while keeping the waveform distortion to a minimum., Comment: submitted for publication, IEEE Transactions on Wireless Communications