Search

The Keyword Spotting (KWS) task involves continuous audio stream monitoring to detect predefined words, requiring low energy devices for continuous processing. Neuromorphic devices effectively address this energy challenge. However, the general neuromorphic KWS pipeline, from microphone to Spiking Neural Network (SNN), entails multiple processing stages. Leveraging the popularity of Pulse Density Modulation (PDM) microphones in modern devices and their similarity to spiking neurons, we propose a direct microphone-to-SNN connection. This approach eliminates intermediate stages, notably reducing computational costs. The system achieved an accuracy of 91.54\% on the Google Speech Command (GSC) dataset, surpassing the state-of-the-art for the Spiking Speech Command (SSC) dataset which is a bio-inspired encoded GSC. Furthermore, the observed sparsity in network activity and connectivity indicates potential for remarkably low energy consumption in a neuromorphic device implementation., Comment: Accepted at INTERSPEECH 2024

Smart contracts, self-executing programs on the blockchain, facilitate reliable value exchanges without centralized oversight. Despite the recent focus on dynamic analysis of their transaction histories in both industry and academia, no open-source tool currently offers comprehensive tracking of complete transaction information to extract user-desired data such as invariant-related data. This paper introduces OpenTracer, designed to address this gap. OpenTracer guarantees comprehensive tracking of every execution step, providing complete transaction information. OpenTracer has been employed to analyze 350,800 Ethereum transactions, successfully inferring 23 different types of invariant from predefined templates. The tool is fully open-sourced, serving as a valuable resource for developers and researchers aiming to study transaction behaviors or extract and validate new invariants from transaction traces. The source code of OpenTracer is available at https://github.com/jeffchen006/OpenTracer.

The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of a single scenario, while their ability to associate instances across different scenes has not yet been explored, which is essential for understanding complex visual content, such as movies with multiple characters and intricate plots. Towards movie understanding, a critical initial step for LVLMs is to unleash the potential of character identities memory and recognition across multiple visual scenarios. To achieve the goal, we propose visual instruction tuning with ID reference and develop an ID-Aware Large Vision-Language Model, IDA-VLM. Furthermore, our research introduces a novel benchmark MM-ID, to examine LVLMs on instance IDs memory and recognition across four dimensions: matching, location, question-answering, and captioning. Our findings highlight the limitations of existing LVLMs in recognizing and associating instance identities with ID reference. This paper paves the way for future artificial intelligence systems to possess multi-identity visual inputs, thereby facilitating the comprehension of complex visual narratives like movies.

Intermediate step methodologies like chain of thoughts (COT) have demonstrated effectiveness in enhancing the performance of Large Language Models (LLMs) on code generation. This study explores the utilization of intermediate languages, including various programming languages, natural language solutions, and pseudo-code, and systematically evaluates their impact on the performance of LLMs in code generation tasks. Our experiments encompass eleven models across the CodeLlama, GPT, and Mistral families, as well as newly released smaller models. Our findings reveal that intermediate languages generally exhibit greater efficacy in larger models that have not yet achieved state-of-the-art performance. Natural language consistently emerges as the most effective intermediate representation across all target languages. However, we observe no universally effective intermediate formal language across different models and target languages. Furthermore, we uncover a weak correlation between the correctness of intermediate solutions and final generation, suggesting that improvements may stem from the chain-of-thought effect rather than language-specific transfer. Interestingly, we discover that for GPT family models, prompting multiple times without explicit self-correction instructions yields performance gains across the studied languages.

Deploying Connected and Automated Vehicles (CAVs) on top of 5G and Beyond networks (5GB) makes them vulnerable to increasing vectors of security and privacy attacks. In this context, a wide range of advanced machine/deep learning based solutions have been designed to accurately detect security attacks. Specifically, supervised learning techniques have been widely applied to train attack detection models. However, the main limitation of such solutions is their inability to detect attacks different from those seen during the training phase, or new attacks, also called zero-day attacks. Moreover, training the detection model requires significant data collection and labeling, which increases the communication overhead, and raises privacy concerns. To address the aforementioned limits, we propose in this paper a novel detection mechanism that leverages the ability of the deep auto-encoder method to detect attacks relying only on the benign network traffic pattern. Using federated learning, the proposed intrusion detection system can be trained with large and diverse benign network traffic, while preserving the CAVs privacy, and minimizing the communication overhead. The in-depth experiment on a recent network traffic dataset shows that the proposed system achieved a high detection rate while minimizing the false positive rate, and the detection delay.

This article conducts an in-depth investigation of a new spatio-temporal model for the cocaine-heroin epidemiological model with vital dynamics, incorporating the Laplacian operator. The study rigorously establishes the existence, uniqueness, non-negativity, and boundedness of solutions for the proposed model. In addition, the local stability of both a drug-free equilibrium and a drug-addiction equilibrium are analyzed by studying the corresponding characteristic equations. The research provides conclusive evidence that when the basic reproductive number $\mathcal{R}_0$ exceeds 1, the drug-addiction equilibrium is globally asymptotically stable. Conversely, using comparative arguments, it is shown that if $\mathcal{R}_0$ is less than 1, the drug-free equilibrium is globally asymptotically stable. Furthermore, the article includes a series of numerical simulations to visually convey and support the analytical results.

In this chapter, we consider a reaction-diffusion SVIR infection model with dis-tributed delay and nonlinear incidence rate. The wellposedness of the proposed model is proved. By means of Lyapunov functionals, we show that the disease-free equilibrium state is globally asymptotically stable when the basic reproduction number is less or equal than one, and that the disease endemic equilibrium is globally asymptotically stable when the basic reproduction number is greater than one. Numerical simulations are provided to illustrate the obtained theoretical results.

The rapid growth of e-commerce has placed considerable pressure on customs representatives, prompting advanced methods. In tackling this, Artificial intelligence (AI) systems have emerged as a promising approach to minimize the risks faced. Given that the Harmonized System (HS) code is a crucial element for an accurate customs declaration, we propose a novel multimodal HS code prediction approach using deep learning models exploiting both image and text features obtained through the customs declaration combined with e-commerce platform information. We evaluated two early fusion methods and introduced our MultConcat fusion method. To the best of our knowledge, few studies analyze the featurelevel combination of text and image in the state-of-the-art for HS code prediction, which heightens interest in our paper and its findings. The experimental results prove the effectiveness of our approach and fusion method with a top-3 and top-5 accuracy of 93.5% and 98.2% respectively, Comment: Accepted for poster presentation at ESANN 2023

Large quantities of random numbers are crucial in a wide range of applications. We have recently demonstrated that perpendicular nanopillar magnetic tunnel junctions (pMTJs) can produce true random bits when actuated with short pulses. However, our implementation used high-end and expensive electronics, such as a high bandwidth arbitrary waveform generator and analog-to-digital converter, and was limited to relatively low data rates. Here, we significantly increase the speed of true random number generation (TRNG) of our stochastic actuated pMTJs (SMART-pMTJs) using Field Programmable Gate Arrays (FPGAs), demonstrating the generation of over $10^{12}$ bits at rates exceeding 10Mb/s. The resulting bitstreams pass the NIST Statistical Test Suite for randomness with only one XOR operation. In addition to a hundred-fold reduction in the setup cost and a thousand-fold increase in bitrate, the advancement includes simplifying and optimizing random bit generation with a custom-designed analog daughter board to interface an FPGA and SMART-pMTJ. The resulting setup further enables FPGA at-speed processing of MTJ data for stochastic modeling and cryptography., Comment: 4 pages, 5 figures

Smart contract transactions associated with security attacks often exhibit distinct behavioral patterns compared with historical benign transactions before the attacking events. While many runtime monitoring and guarding mechanisms have been proposed to validate invariants and stop anomalous transactions on the fly, the empirical effectiveness of the invariants used remains largely unexplored. In this paper, we studied 23 prevalent invariants of 8 categories, which are either deployed in high-profile protocols or endorsed by leading auditing firms and security experts. Using these well-established invariants as templates, we developed a tool Trace2Inv which dynamically generates new invariants customized for a given contract based on its historical transaction data. We evaluated Trace2Inv on 42 smart contracts that fell victim to 27 distinct exploits on the Ethereum blockchain. Our findings reveal that the most effective invariant guard alone can successfully block 18 of the 27 identified exploits with minimal gas overhead. Our analysis also shows that most of the invariants remain effective even when the experienced attackers attempt to bypass them. Additionally, we studied the possibility of combining multiple invariant guards, resulting in blocking up to 23 of the 27 benchmark exploits and achieving false positive rates as low as 0.32%. Trace2Inv outperforms current state-of-the-art works on smart contract invariant mining and transaction attack detection in terms of both practicality and accuracy. Though Trace2Inv is not primarily designed for transaction attack detection, it surprisingly found two previously unreported exploit transactions, earlier than any reported exploit transactions against the same victim contracts.

This paper deals with a new epidemiological model of SIRS with stochastic perturbations. The primary objective is to establish the existence of a unique non-negative nonlocal solution. Using the basic reproduction number $\mathscr{R}_0$ derived from the associated deterministic model, we demonstrate the existence of a stationary distribution in the stochastic model. In addition, we study the fluctuation of the unique solution of the deterministic problem around the disease-free equilibrium under certain conditions. In particular, we reveal scenarios where random effects induce disease extinction, contrary to the persistence predicted by the deterministic model. The theoretical insights are complemented by numerical simulations, which provide further validation of our findings.

This paper proposes to correct the rolling shutter (RS) distorted images by estimating the distortion flow from the global shutter (GS) to RS directly. Existing methods usually perform correction using the undistortion flow from the RS to GS. They initially predict the flow from consecutive RS frames, subsequently rescaling it as the displacement fields from the RS frame to the underlying GS image using time-dependent scaling factors. Following this, RS-aware forward warping is employed to convert the RS image into its GS counterpart. Nevertheless, this strategy is prone to two shortcomings. First, the undistortion flow estimation is rendered inaccurate by merely linear scaling the flow, due to the complex non-linear motion nature. Second, RS-aware forward warping often results in unavoidable artifacts. To address these limitations, we introduce a new framework that directly estimates the distortion flow and rectifies the RS image with the backward warping operation. More specifically, we first propose a global correlation-based flow attention mechanism to estimate the initial distortion flow and GS feature jointly, which are then refined by the following coarse-to-fine decoder layers. Additionally, a multi-distortion flow prediction strategy is integrated to mitigate the issue of inaccurate flow estimation further. Experimental results validate the effectiveness of the proposed method, which outperforms state-of-the-art approaches on various benchmarks while maintaining high efficiency. The project is available at \url{https://github.com/ljzycmd/DFRSC}., Comment: CVPR2024

Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However, this assumption does not always hold in real-world scenarios due to divergent distributions, different class sets, and asymmetrical information representation. As conventional GANs attempt to generate images that match the distribution of the target domain, they may hallucinate spurious instances of classes absent from the source domain, thereby diminishing the usefulness and reliability of translated images. CycleGAN-based methods are also known to hide the mismatched information in the generated images to bypass cycle consistency objectives, a process known as steganography. In response to the challenge of non-bijective image translation, we introduce StegoGAN, a novel model that leverages steganography to prevent spurious features in generated images. Our approach enhances the semantic consistency of the translated images without requiring additional postprocessing or supervision. Our experimental evaluations demonstrate that StegoGAN outperforms existing GAN-based models across various non-bijective image-to-image translation tasks, both qualitatively and quantitatively. Our code and pretrained models are accessible at https://github.com/sian-wusidi/StegoGAN.

The widespread use of high-definition screens in edge devices, such as end-user cameras, smartphones, and televisions, is spurring a significant demand for image enhancement. Existing enhancement models often optimize for high performance while falling short of reducing hardware inference time and power consumption, especially on edge devices with constrained computing and storage resources. To this end, we propose Image Color Enhancement Lookup Table (ICELUT) that adopts LUTs for extremely efficient edge inference, without any convolutional neural network (CNN). During training, we leverage pointwise (1x1) convolution to extract color information, alongside a split fully connected layer to incorporate global information. Both components are then seamlessly converted into LUTs for hardware-agnostic deployment. ICELUT achieves near-state-of-the-art performance and remarkably low power consumption. We observe that the pointwise network structure exhibits robust scalability, upkeeping the performance even with a heavily downsampled 32x32 input image. These enable ICELUT, the first-ever purely LUT-based image enhancer, to reach an unprecedented speed of 0.4ms on GPU and 7ms on CPU, at least one order faster than any CNN solution. Codes are available at https://github.com/Stephen0808/ICELUT., Comment: Accepted by ECCV2024

Physics-informed neural networks (PINNs) have successfully addressed various computational physics problems based on partial differential equations (PDEs). However, while tackling issues related to irregularities like singularities and oscillations, trained solutions usually suffer low accuracy. In addition, most current works only offer the trained solution for predetermined input parameters. If any change occurs in input parameters, transfer learning or retraining is required, and traditional numerical techniques also need an independent simulation. In this work, a physics-driven GraphSAGE approach (PD-GraphSAGE) based on the Galerkin method and piecewise polynomial nodal basis functions is presented to solve computational problems governed by irregular PDEs and to develop parametric PDE surrogate models. This approach employs graph representations of physical domains, thereby reducing the demands for evaluated points due to local refinement. A distance-related edge feature and a feature mapping strategy are devised to help training and convergence for singularity and oscillation situations, respectively. The merits of the proposed method are demonstrated through a couple of cases. Moreover, the robust PDE surrogate model for heat conduction problems parameterized by the Gaussian random field source is successfully established, which not only provides the solution accurately but is several times faster than the finite element method in our experiments., Comment: 18 pages,11 figures, 3 tables

In this note, we present a simple proof of an analogue of the Cauchy-Schwarz inequality relevant to products of determinants. Specifically, we show that $$ |\det(A^*MB)|^2\leq \det(A^*MA)\cdot \det(B^*MB),\quad A,B\in \mathbb{C}^{m\times n},$$ where $M\in\mathbb{C}^{m\times m}$ is hermitian positive definite. Here $m$ and $n$ are arbitrary. In case $m\leq n$, equality holds trivially. Equality holds when $m>n$ and $\text{rank}(A)=\text{rank}(B)=n$ if and only if the columns of $A$ and the columns of $B$ span the same subspace of $\mathbb{C}^m$., Comment: 7

In this work we study a fractional SEIR biological model of a reaction-diffusion, using the non-singular kernel Caputo-Fabrizio fractional derivative in the Caputo sense and employing the Laplacian operator. In our PDE model, the government seeks immunity through the vaccination program, which is considered a control variable. Our study aims to identify the ideal control pair that reduces the number of infected/infectious people and the associated vaccine and treatment costs over a limited time and space. Moreover, by using the forward-backward algorithm, the approximate results are explained by dynamic graphs to monitor the effectiveness of vaccination.

The primary objective of non-intrusive load monitoring (NILM) techniques is to monitor and track power consumption within residential buildings. This is achieved by approximating the consumption of each individual appliance from the aggregate energy measurements. Event-based NILM solutions are generally more accurate than other methods. Our paper introduces a novel event detection algorithm called Tukey's Fences-based event detector (TFED). This algorithm uses the fast Fourier transform in conjunction with the Tukey fences rule to detect variations in the aggregated current signal. The primary benefit of TFED is its superior ability to accurately pinpoint the start times of events, as demonstrated through simulations. Our findings reveal that the proposed algorithm boasts an impressive 99% accuracy rate, surpassing the accuracy of other recent works in the literature such as the Cepstrum and $\chi ^2$ GOF statistic-based analyses, which only achieved 98% accuracy.

This paper investigates a novel nonlinear singular fractional SI model with the $\Phi_p$ operator and the Mittag-Leffler kernel. The initial investigation includes the existence, uniqueness, boundedness, and non-negativity of the solution. We then establish Hyers-Ulam stability for the proposed model in Banach space. Optimal control analysis is performed to minimize the spread of infection and maximize the population of susceptible individuals. Finally, the theoretical results are supported by numerical simulations., Comment: 22 pages

We demonstrate the miniaturization of perpendicularly magnetized superparamagnetic tunnel junctions (SMTJs) down to 50 nm in diameter. We experimentally show stochastic reversals in those junctions, with tunable mean dwell times down to a few nanoseconds through applied magnetic field and voltage. The mean dwell times measured at negligible bias voltage agree with our simulations based on Langer's theory. We shed light on an Arrhenius prefactor $\tau_0$ of a few femtoseconds, implying that the rates of thermally-activated magnetic transitions exceed the GHz-to-THz limitation of macrospin models, whereby $\tau_0\sim1$ ns. We explain the small prefactor values by a Meyer-Neldel compensation phenomenon, where the prefactor exhibits a large entropic contribution with an exponential dependence on the activation energy. These findings pave the way towards the development of ultrafast, low-power unconventional computing schemes operating by leveraging thermal noise in perpendicular SMTJs, which are scalable below 20 nm., Comment: 7 pages, 3 figures

We report on the conception, fabrication and characterization of a new concept of optical fiber enabling a precise control of the ratio between the 2nd and 4th-order of chromatic dispersion (respectively \b{eta}2 and \b{eta}4) at 1.55 micro-meter which is at the heart of the Four-Wave-Mixing (FWM) generation. For conventional highly nonlinear fiber the sensitivity of this ratio to fiber geometry fluctuations is very critical, making the fabrication process challenging. The new design fiber reconciles the accurate control of chromatic dispersion properties and fabrication by standard stack and draw method, allowing a robust and reliable method against detrimental fluctuations parameters during the fabrication process. Experimental frequency conversion with FWM in the new design fiber is demonstrated., Comment: 9 pages, 6 figures

This paper presents OVer, a framework designed to automatically analyze the behavior of decentralized finance (DeFi) protocols when subjected to a "skewed" oracle input. OVer firstly performs symbolic analysis on the given contract and constructs a model of constraints. Then, the framework leverages an SMT solver to identify parameters that allow its secure operation. Furthermore, guard statements may be generated for smart contracts that may use the oracle values, thus effectively preventing oracle manipulation attacks. Empirical results show that OVer can successfully analyze all 10 benchmarks collected, which encompass a diverse range of DeFi protocols. Additionally, this paper also illustrates that current parameters utilized in the majority of benchmarks are inadequate to ensure safety when confronted with significant oracle deviations., Comment: 13 pages; extended version of paper accepted in ICSE'24

Unbiased sources of true randomness are critical for the successful deployment of stochastic unconventional computing schemes and encryption applications in hardware. Leveraging nanoscale thermal magnetization fluctuations provides an efficient and almost cost-free means of generating truly random bitstreams, distinguishing them from predictable pseudo-random sequences. However, existing approaches that aim to achieve randomness often suffer from bias, leading to significant deviations from equal fractions of 0 and 1 in the bitstreams and compromising their inherent unpredictability. This study presents a hardware approach that capitalizes on the intrinsic balance of phase noise in an oscillator injection locked at twice its natural frequency, leveraging the stability of this naturally balanced physical system. We demonstrate the successful generation of unbiased and truly random bitstreams through extensive experimentation. Our numerical simulations exhibit excellent agreement with the experimental results, confirming the robustness and viability of our approach., Comment: 13 pages, 8 figures

Historical maps provide useful spatio-temporal information on the Earth's surface before modern earth observation techniques came into being. To extract information from maps, neural networks, which gain wide popularity in recent years, have replaced hand-crafted map processing methods and tedious manual labor. However, aleatoric uncertainty, known as data-dependent uncertainty, inherent in the drawing/scanning/fading defects of the original map sheets and inadequate contexts when cropping maps into small tiles considering the memory limits of the training process, challenges the model to make correct predictions. As aleatoric uncertainty cannot be reduced even with more training data collected, we argue that complementary spatio-temporal contexts can be helpful. To achieve this, we propose a U-Net-based network that fuses spatio-temporal features with cross-attention transformers (U-SpaTem), aggregating information at a larger spatial range as well as through a temporal sequence of images. Our model achieves a better performance than other state-or-art models that use either temporal or spatial contexts. Compared with pure vision transformers, our model is more lightweight and effective. To the best of our knowledge, leveraging both spatial and temporal contexts have been rarely explored before in the segmentation task. Even though our application is on segmenting historical maps, we believe that the method can be transferred into other fields with similar problems like temporal sequences of satellite images. Our code is freely accessible at https://github.com/chenyizi086/wu.2023.sigspatial.git.

Learning operators mapping between infinite-dimensional Banach spaces via neural networks has attracted a considerable amount of attention in recent years. In this paper, we propose an interfaced operator network (IONet) to solve parametric elliptic interface PDEs, where different coefficients, source terms, and boundary conditions are considered as input features. To capture the discontinuities in both the input functions and the output solutions across the interface, IONet divides the entire domain into several separate subdomains according to the interface and uses multiple branch nets and trunk nets. Each branch net extracts latent representations of input functions at a fixed number of sensors on a specific subdomain, and each trunk net is responsible for output solutions on one subdomain. Additionally, tailored physics-informed loss of IONet is proposed to ensure physical consistency, which greatly reduces the training dataset requirement and makes IONet effective without any paired input-output observations inside the computational domain. Extensive numerical studies demonstrate that IONet outperforms existing state-of-the-art deep operator networks in terms of accuracy and versatility.