Search

Federated Learning (FL) performance is highly influenced by data distribution across clients, and non-Independent and Identically Distributed (non-IID) leads to a slower convergence of the global model and a decrease in model effectiveness. The existing algorithms for solving the non-IID problem are focused on the traditional centralized FL (CFL), where a central server is used for model aggregation. However, in decentralized FL (DFL), nodes lack the overall vision of the federation. To address the non-IID problem in DFL, this paper proposes a novel DFL aggregation algorithm, Federated Entropy Pooling (FedEP). FedEP mitigates the client drift problem by incorporating the statistical characteristics of local distributions instead of any actual data. Prior to training, each client conducts a local distribution fitting using a Gaussian Mixture Model (GMM) and shares the resulting statistical characteristics with its neighbors. After receiving the statistical characteristics shared by its neighbors, each node tries to fit the global data distribution. In the aggregation phase, each node calculates the Kullback-Leibler (KL) divergences of the local data distribution over the fitted global data distribution, giving the weights to generate the aggregated model. Extensive experiments have demonstrated that FedEP can achieve faster convergence and show higher test performance than state-of-the-art approaches.

Federated Learning (FL), introduced in 2016, was designed to enhance data privacy in collaborative model training environments. Among the FL paradigm, horizontal FL, where clients share the same set of features but different data samples, has been extensively studied in both centralized and decentralized settings. In contrast, Vertical Federated Learning (VFL), which is crucial in real-world decentralized scenarios where clients possess different, yet sensitive, data about the same entity, remains underexplored. Thus, this work introduces De-VertiFL, a novel solution for training models in a decentralized VFL setting. De-VertiFL contributes by introducing a new network architecture distribution, an innovative knowledge exchange scheme, and a distributed federated training process. Specifically, De-VertiFL enables the sharing of hidden layer outputs among federation clients, allowing participants to benefit from intermediate computations, thereby improving learning efficiency. De-VertiFL has been evaluated using a variety of well-known datasets, including both image and tabular data, across binary and multiclass classification tasks. The results demonstrate that De-VertiFL generally surpasses state-of-the-art methods in F1-score performance, while maintaining a decentralized and privacy-preserving framework.

Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume Independently and Identically Distributed (IID) data, which is unrealistic in real-world applications. In non-IID contexts, existing defensive strategies face challenges in distinguishing between models that have been compromised and those that have been trained on heterogeneous data distributions, leading to diminished efficacy. In response, this paper proposes a framework that employs the Moving Target Defense (MTD) approach to bolster the robustness of DFL models. By continuously modifying the attack surface of the DFL system, this framework aims to mitigate poisoning attacks effectively. The proposed MTD framework includes both proactive and reactive modes, utilizing a reputation system that combines metrics of model similarity and loss, alongside various defensive techniques. Comprehensive experimental evaluations indicate that the MTD-based mechanism significantly mitigates a range of poisoning attack types across multiple datasets with different topologies.

Open-ended questions test a more thorough understanding than closed-ended questions and are often a preferred assessment method. However, open-ended questions are tedious to grade and subject to personal bias. Therefore, there have been efforts to speed up the grading process through automation. Short Answer Grading (SAG) systems aim to automatically score students' answers. Despite growth in SAG methods and capabilities, there exists no comprehensive short-answer grading benchmark across different subjects, grading scales, and distributions. Thus, it is hard to assess the capabilities of current automated grading methods in terms of their generalizability. In this preliminary work, we introduce the combined ASAG2024 benchmark to facilitate the comparison of automated grading systems. Combining seven commonly used short-answer grading datasets in a common structure and grading scale. For our benchmark, we evaluate a set of recent SAG methods, revealing that while LLM-based approaches reach new high scores, they still are far from reaching human performance. This opens up avenues for future research on human-machine SAG systems., Comment: Accepted at SIGCSE-Virtual 2024

An all-fiber dual Mach-Zehnder interferometer (MZI) based on an acoustically modulated hollow-core fiber (HCF) is experimentally demonstrated for the first time. By attaching an acoustic driver in between the fixed ends of an HCF, we fabricated two acousto-optic modulators (AOMs) with distinct driver positions, allowing for synchronizing two in-line MZIs inside the HCF. The first MZI is set by two acoustic long-period gratings separated by a second MZI formed at the fiber and driver attaching region. We show that this setup enables frequency-tuning of the coupling between the fundamental and higher-order modes in the HCF. Additionally, we simulate and analyze the HCF modal couplings and MZIs' modulated spectra under distinct device parameters using the transfer matrix method. The new AOM-MZI enables tuning of the MZIs free spectral range by adjusting 1 Hz of the electrical frequency, which is promising to modulate multiwavelength filters, sensors and fiber lasers.

In non-star-forming, passively evolving galaxies, regions with emission lines dominated by low-ionization species are classified as Low-Ionization Emission Regions (LIERs). The ionization mechanism behind such regions has long been a mystery. Active Galactic Nuclei (AGNs), which were once believed to be the source, have been found not to be the dominant mechanism, especially in regions distant from the galaxy nuclei. The remaining candidates, photoionization by post-Asymtopic Giant Branch (pAGB) stars and interstellar shocks can only be distinguished with in-depth analysis. As the temperature predictions of these two models differ, temperature measurements can provide strong constraints on this puzzle. We selected a sample of 2795 quiescent red-sequence galaxies from the Sloan Digital Sky Survey IV (SDSS-IV) Mapping Nearby Galaxies at Apache Point Observatory (MaNGA) survey. We divided the sample spectra into three groups based on their [N II]/H$\alpha$ flux ratio and utilized stacking techniques to improve the signal-to-noise ratio of the observed spectra. We determined the temperature of [O III], [N II], [S II], and [O II] through their temperature-sensitive emission line ratios. Subsequently, we compared the measured temperatures with predictions from different models. The results demonstrate consistency with the interstellar shock model with preshock density n = 1 cm$^{-3}$ and solar metallicity, thus supporting shocks as the dominant ionization source of LIERs. Additionally, we also find that the interstellar dust extinction value measured through the Balmer decrement appears to be larger than that implied by the forbidden line ratios of low-ionization lines., Comment: 17 pages, 14 figures, Accepted by A&A

Federated Learning (FL) has emerged as a promising approach to address privacy concerns inherent in Machine Learning (ML) practices. However, conventional FL methods, particularly those following the Centralized FL (CFL) paradigm, utilize a central server for global aggregation, which exhibits limitations such as bottleneck and single point of failure. To address these issues, the Decentralized FL (DFL) paradigm has been proposed, which removes the client-server boundary and enables all participants to engage in model training and aggregation tasks. Nevertheless, as CFL, DFL remains vulnerable to adversarial attacks, notably poisoning attacks that undermine model performance. While existing research on model robustness has predominantly focused on CFL, there is a noteworthy gap in understanding the model robustness of the DFL paradigm. In this paper, a thorough review of poisoning attacks targeting the model robustness in DFL systems, as well as their corresponding countermeasures, are presented. Additionally, a solution called DART is proposed to evaluate the robustness of DFL models, which is implemented and integrated into a DFL platform. Through extensive experiments, this paper compares the behavior of CFL and DFL under diverse poisoning attacks, pinpointing key factors affecting attack spread and effectiveness within the DFL. It also evaluates the performance of different defense mechanisms and investigates whether defense mechanisms designed for CFL are compatible with DFL. The empirical results provide insights into research challenges and suggest ways to improve the robustness of DFL models for future research.

Prompting and Multiple Choices Questions (MCQ) have become the preferred approach to assess the capabilities of Large Language Models (LLMs), due to their ease of manipulation and evaluation. Such experimental appraisals have pointed toward the LLMs' apparent ability to perform causal reasoning or to grasp uncertainty. In this paper, we investigate whether these abilities are measurable outside of tailored prompting and MCQ by reformulating these issues as direct text completion - the foundation of LLMs. To achieve this goal, we define scenarios with multiple possible outcomes and we compare the prediction made by the LLM through prompting (their Stated Answer) to the probability distributions they compute over these outcomes during next token prediction (their Revealed Belief). Our findings suggest that the Revealed Belief of LLMs significantly differs from their Stated Answer and hint at multiple biases and misrepresentations that their beliefs may yield in many scenarios and outcomes. As text completion is at the core of LLMs, these results suggest that common evaluation methods may only provide a partial picture and that more research is needed to assess the extent and nature of their capabilities.

Differential privacy (DP) has the potential to enable privacy-preserving analysis on sensitive data, but requires analysts to judiciously spend a limited ``privacy loss budget'' $\epsilon$ across queries. Analysts conducting exploratory analyses do not, however, know all queries in advance and seldom have DP expertise. Thus, they are limited in their ability to specify $\epsilon$ allotments across queries prior to an analysis. To support analysts in spending $\epsilon$ efficiently, we propose a new interactive analysis paradigm, Measure-Observe-Remeasure, where analysts ``measure'' the database with a limited amount of $\epsilon$, observe estimates and their errors, and remeasure with more $\epsilon$ as needed. We instantiate the paradigm in an interactive visualization interface which allows analysts to spend increasing amounts of $\epsilon$ under a total budget. To observe how analysts interact with the Measure-Observe-Remeasure paradigm via the interface, we conduct a user study that compares the utility of $\epsilon$ allocations and findings from sensitive data participants make to the allocations and findings expected of a rational agent who faces the same decision task. We find that participants are able to use the workflow relatively successfully, including using budget allocation strategies that maximize over half of the available utility stemming from $\epsilon$ allocation. Their loss in performance relative to a rational agent appears to be driven more by their inability to access information and report it than to allocate $\epsilon$., Comment: Published in IEEE Symposium on Security and Privacy (SP) 2024

Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, which could prove difficult in some settings. In this work, we present a novel method based on the expectation-maximization algorithm for training diffusion models from incomplete and noisy observations only. Unlike previous works, our method leads to proper diffusion models, which is crucial for downstream tasks. As part of our method, we propose and motivate an improved posterior sampling scheme for unconditional diffusion models. We present empirical evidence supporting the effectiveness of our method.

In the current cybersecurity landscape, protecting military devices such as communication and battlefield management systems against sophisticated cyber attacks is crucial. Malware exploits vulnerabilities through stealth methods, often evading traditional detection mechanisms such as software signatures. The application of ML/DL in vulnerability detection has been extensively explored in the literature. However, current ML/DL vulnerability detection methods struggle with understanding the context and intent behind complex attacks. Integrating large language models (LLMs) with system call analysis offers a promising approach to enhance malware detection. This work presents a novel framework leveraging LLMs to classify malware based on system call data. The framework uses transfer learning to adapt pre-trained LLMs for malware detection. By retraining LLMs on a dataset of benign and malicious system calls, the models are refined to detect signs of malware activity. Experiments with a dataset of over 1TB of system calls demonstrate that models with larger context sizes, such as BigBird and Longformer, achieve superior accuracy and F1-Score of approximately 0.86. The results highlight the importance of context size in improving detection rates and underscore the trade-offs between computational complexity and performance. This approach shows significant potential for real-time detection in high-stakes environments, offering a robust solution to evolving cyber threats., Comment: Submitted to IEEE MILCOM 2024

We demonstrate the acousto-optic modulation of a hybrid-lattice hollow core fiber (HL-HCF) for the first time. For many years, optical fibers with reduced diameters have been the main solution to increase the interaction of acoustic and optical waves. However, the high drive voltages and large modulator components still employed drastically affect the efficiency and miniaturization of these devices. Here, we experimentally show that combining Kagom\'e and tubular lattices in HL-HCFs allows for enhancing the amplification of the acoustic waves and the modulation of the guided optical modes thus providing high modulation efficiency even when using a fiber with a 240 um diameter. To the best of our knowledge, the measured HL-HCF's modulation efficiency (1.3 dB/V) is the highest compared to devices employing reduced diameter fibers. Additionally, we demonstrate a compact acousto-optic modulator with driver dimensions smaller than the HL-HCF diameter. Overall, our results show a promising alternative to solve the compromise of speed, efficiency, and compactness for integration with microscale all-fiber photonic devices.

Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initializing a data generating model by pre-training on public data has shown to improve the quality of synthetic data, but this technique is not applicable when model structure is not determined a priori. We develop the mechanism jam-pgm, which expands the adaptive measurements framework to jointly select between measuring public data and private data. This technique allows for public data to be included in a graphical-model-based mechanism. We show that jam-pgm is able to outperform both publicly assisted and non publicly assisted synthetic data generation mechanisms even when the public data distribution is biased.

Threat modeling is a popular method to securely develop systems by achieving awareness of potential areas of future damage caused by adversaries. However, threat modeling for systems relying on Artificial Intelligence is still not well explored. While conventional threat modeling methods and tools did not address AI-related threats, research on this amalgamation still lacks solutions capable of guiding and automating the process, as well as providing evidence that the methods hold up in practice. Consequently, this paper presents ThreatFinderAI, an approach and tool providing guidance and automation to model AI-related assets, threats, countermeasures, and quantify residual risks. To evaluate the practicality of the approach, participants were tasked to recreate a threat model developed by cybersecurity experts of an AI-based healthcare platform. Secondly, the approach was used to identify and discuss strategic risks in an LLM-based application through a case study. Overall, the solution's usability was well-perceived and effectively supports threat identification and risk discussion.

The modulation efficiency of a tubular-lattice hollow-core fiber (HCF) by means of flexural acoustic waves is investigated in detail for the first time. The main acousto-optic properties of the HCF are evaluated employing 2D and 3D models based on the finite element method. The induced coupling of the fundamental and first higher-order modes is simulated in the wavelength range from 743 to 1355 nm. Significant acoustic (amplitude, period, strain, energy) and optical parameters (effective index, beat length, birefringence, coupling coefficient) are analyzed. The simulations are compared to experimental results, indicating higher modulation performance in HCFs compared to standard optical fibers. In addition, useful insights into the design and fabrication of all-fiber acousto-optic devices based on HCFs are provided, enabling potential application in tunable spectral filters and mode-locked fiber lasers.

Although ransomware has received broad attention in media and research, this evolving threat vector still poses a systematic threat. Related literature has explored their detection using various approaches leveraging Machine and Deep Learning. While these approaches are effective in detecting malware, they do not answer how to use this intelligence to protect against threats, raising concerns about their applicability in a hostile environment. Solutions that focus on mitigation rarely explore how to prevent and not just alert or halt its execution, especially when considering Linux-based samples. This paper presents GuardFS, a file system-based approach to investigate the integration of detection and mitigation of ransomware. Using a bespoke overlay file system, data is extracted before files are accessed. Models trained on this data are used by three novel defense configurations that obfuscate, delay, or track access to the file system. The experiments on GuardFS test the configurations in a reactive setting. The results demonstrate that although data loss cannot be completely prevented, it can be significantly reduced. Usability and performance analysis demonstrate that the defense effectiveness of the configurations relates to their impact on resource consumption and usability.

The dark web has become notorious for its association with illicit activities and there is a growing need for systems to automate the monitoring of this space. This paper proposes an end-to-end scalable architecture for the early identification of new Tor sites and the daily analysis of their content. The solution is built using an Open Source Big Data stack for data serving with Kubernetes, Kafka, Kubeflow, and MinIO, continuously discovering onion addresses in different sources (threat intelligence, code repositories, web-Tor gateways, and Tor repositories), downloading the HTML from Tor and deduplicating the content using MinHash LSH, and categorizing with the BERTopic modeling (SBERT embedding, UMAP dimensionality reduction, HDBSCAN document clustering and c-TF-IDF topic keywords). In 93 days, the system identified 80,049 onion services and characterized 90% of them, addressing the challenge of Tor volatility. A disproportionate amount of repeated content is found, with only 6.1% unique sites. From the HTML files of the dark sites, 31 different low-topics are extracted, manually labeled, and grouped into 11 high-level topics. The five most popular included sexual and violent content, repositories, search engines, carding, cryptocurrencies, and marketplaces. During the experiments, we identified 14 sites with 13,946 clones that shared a suspiciously similar mirroring rate per day, suggesting an extensive common phishing network. Among the related works, this study is the most representative characterization of onion services based on topics to date.

We report on high-temperature sensing measurements using a tubular-lattice hollow-core photonic crystal fiber displaying a microstructure formed of eight 2.4 um-thick cladding tubes. The larger thickness of our fiber's cladding tubes compared to other hollow fibers operating in the visible and infrared ranges entails multiple narrow transmission bands in its transmission spectrum (6 bands in the spectral range between 400 nm and 950 nm) and benefits the realization of the temperature sensing measurements. The principle of operation of our device is based on the thermo-optic effect and thermal expansion-induced spectral shifts of the fiber transmission bands due to temperature variations. To study the sensor operation, we monitored the fiber transmission bands' spectral positions from room temperature to 1085 oC in both ramp-up and ramp-down scenarios. Additionally, we investigated the optimization opportunities by assessing an analytical model describing the fiber transmission characteristics and discussed the alternatives for enhancing the sensor performance. Moreover, our fiber characterization experiments revealed a consistent confinement loss trend aligned with the scaling laws in tubular-lattice hollow-core fibers. We thus understand that the results presented in this manuscript highlight a relevant path for the development of temperature sensors based on microstructured hollow-core optical fibers endowed with thick cladding tubes.

We demonstrate a broadband acousto-optic notch filter based on a tubular-lattice hollow-core fiber for the first time. The guided optical modes are modulated by acoustically induced dynamic long-period gratings along the fiber. The device is fabricated employing a short interaction length (7.7 cm) and low drive voltages (10 V). Modulated spectral bands with 20 nm half-width and maximum depths greater than 60 % are achieved. The resonant notch wavelength is tuned from 743 to 1355 nm (612 nm span) by changing the frequency of the electrical signal. The results indicate a broader tuning range compared to previous studies using standard and hollow-core fibers. It further reveals unique properties for reconfigurable spectral filters and fiber lasers, pointing to the fast switching and highly efficient modulation of all-fiber photonic devices.

Artificial intelligence (AI) plays a pivotal role in various sectors, influencing critical decision-making processes in our daily lives. Within the AI landscape, novel AI paradigms, such as Federated Learning (FL), focus on preserving data privacy while collaboratively training AI models. In such a context, a group of experts from the European Commission (AI-HLEG) has identified sustainable AI as one of the key elements that must be considered to provide trustworthy AI. While existing literature offers several taxonomies and solutions for assessing the trustworthiness of FL models, a significant gap exists in considering sustainability and the carbon footprint associated with FL. Thus, this work introduces the sustainability pillar to the most recent and comprehensive trustworthy FL taxonomy, making this work the first to address all AI-HLEG requirements. The sustainability pillar assesses the FL system environmental impact, incorporating notions and metrics for hardware efficiency, federation complexity, and energy grid carbon intensity. Then, this work designs and implements an algorithm for evaluating the trustworthiness of FL models by incorporating the sustainability pillar. Extensive evaluations with the FederatedScope framework and various scenarios varying federation participants, complexities, hardware, and energy grids demonstrate the usefulness of the proposed solution.

The growing concern over malicious attacks targeting the robustness of both Centralized and Decentralized Federated Learning (FL) necessitates novel defensive strategies. In contrast to the centralized approach, Decentralized FL (DFL) has the advantage of utilizing network topology and local dataset information, enabling the exploration of Moving Target Defense (MTD) based approaches. This work presents a theoretical analysis of the influence of network topology on the robustness of DFL models. Drawing inspiration from these findings, a three-stage MTD-based aggregation protocol, called Voyager, is proposed to improve the robustness of DFL models against poisoning attacks by manipulating network topology connectivity. Voyager has three main components: an anomaly detector, a network topology explorer, and a connection deployer. When an abnormal model is detected in the network, the topology explorer responds strategically by forming connections with more trustworthy participants to secure the model. Experimental evaluations show that Voyager effectively mitigates various poisoning attacks without imposing significant resource and computational burdens on participants. These findings highlight the proposed reactive MTD as a potent defense mechanism in the context of DFL.

Decentralized Federated Learning (DFL) emerges as an innovative paradigm to train collaborative models, addressing the single point of failure limitation. However, the security and trustworthiness of FL and DFL are compromised by poisoning attacks, negatively impacting its performance. Existing defense mechanisms have been designed for centralized FL and they do not adequately exploit the particularities of DFL. Thus, this work introduces Sentinel, a defense strategy to counteract poisoning attacks in DFL. Sentinel leverages the accessibility of local data and defines a three-step aggregation protocol consisting of similarity filtering, bootstrap validation, and normalization to safeguard against malicious model updates. Sentinel has been evaluated with diverse datasets and data distributions. Besides, various poisoning attack types and threat levels have been verified. The results improve the state-of-the-art performance against both untargeted and targeted poisoning attacks when data follows an IID (Independent and Identically Distributed) configuration. Besides, under non-IID configuration, it is analyzed how performance degrades both for Sentinel and other state-of-the-art robust aggregation methods.

Recent research has shown that the integration of Reinforcement Learning (RL) with Moving Target Defense (MTD) can enhance cybersecurity in Internet-of-Things (IoT) devices. Nevertheless, the practicality of existing work is hindered by data privacy concerns associated with centralized data processing in RL, and the unsatisfactory time needed to learn right MTD techniques that are effective against a rising number of heterogeneous zero-day attacks. Thus, this work presents CyberForce, a framework that combines Federated and Reinforcement Learning (FRL) to collaboratively and privately learn suitable MTD techniques for mitigating zero-day attacks. CyberForce integrates device fingerprinting and anomaly detection to reward or penalize MTD mechanisms chosen by an FRL-based agent. The framework has been deployed and evaluated in a scenario consisting of ten physical devices of a real IoT platform affected by heterogeneous malware samples. A pool of experiments has demonstrated that CyberForce learns the MTD technique mitigating each attack faster than existing RL-based centralized approaches. In addition, when various devices are exposed to different attacks, CyberForce benefits from knowledge transfer, leading to enhanced performance and reduced learning time in comparison to recent works. Finally, different aggregation algorithms used during the agent learning process provide CyberForce with notable robustness to malicious attacks.

The rise of Decentralized Federated Learning (DFL) has enabled the training of machine learning models across federated participants, fostering decentralized model aggregation and reducing dependence on a server. However, this approach introduces unique communication security challenges that have yet to be thoroughly addressed in the literature. These challenges primarily originate from the decentralized nature of the aggregation process, the varied roles and responsibilities of the participants, and the absence of a central authority to oversee and mitigate threats. Addressing these challenges, this paper first delineates a comprehensive threat model focused on DFL communications. In response to these identified risks, this work introduces a security module to counter communication-based attacks for DFL platforms. The module combines security techniques such as symmetric and asymmetric encryption with Moving Target Defense (MTD) techniques, including random neighbor selection and IP/port switching. The security module is implemented in a DFL platform, Fedstellar, allowing the deployment and monitoring of the federation. A DFL scenario with physical and virtual deployments have been executed, encompassing three security configurations: (i) a baseline without security, (ii) an encrypted configuration, and (iii) a configuration integrating both encryption and MTD techniques. The effectiveness of the security module is validated through experiments with the MNIST dataset and eclipse attacks. The results showed an average F1 score of 95%, with the most secure configuration resulting in CPU usage peaking at 68% (+-9%) in virtual deployments and network traffic reaching 480.8 MB (+-18 MB), effectively mitigating risks associated with eavesdropping or eclipse attacks.

Ransomware has remained one of the most notorious threats in the cybersecurity field. Moving Target Defense (MTD) has been proposed as a novel paradigm for proactive defense. Although various approaches leverage MTD, few of them rely on the operating system and, specifically, the file system, thereby making them dependent on other computing devices. Furthermore, existing ransomware defense techniques merely replicate or detect attacks, without preventing them. Thus, this paper introduces the MTFS overlay file system and the design and implementation of three novel MTD techniques implemented on top of it. One delaying attackers, one trapping recursive directory traversal, and another one hiding file types. The effectiveness of the techniques are shown in two experiments. First, it is shown that the techniques can delay and mitigate ransomware on real IoT devices. Secondly, in a broader scope, the solution was confronted with 14 ransomware samples, highlighting that it can save 97% of the files.

Cybersecurity solutions have shown promising performance when detecting ransomware samples that use fixed algorithms and encryption rates. However, due to the current explosion of Artificial Intelligence (AI), sooner than later, ransomware (and malware in general) will incorporate AI techniques to intelligently and dynamically adapt its encryption behavior to be undetected. It might result in ineffective and obsolete cybersecurity solutions, but the literature lacks AI-powered ransomware to verify it. Thus, this work proposes RansomAI, a Reinforcement Learning-based framework that can be integrated into existing ransomware samples to adapt their encryption behavior and stay stealthy while encrypting files. RansomAI presents an agent that learns the best encryption algorithm, rate, and duration that minimizes its detection (using a reward mechanism and a fingerprinting intelligent detection system) while maximizing its damage function. The proposed framework was validated in a ransomware, Ransomware-PoC, that infected a Raspberry Pi 4, acting as a crowdsensor. A pool of experiments with Deep Q-Learning and Isolation Forest (deployed on the agent and detection system, respectively) has demonstrated that RansomAI evades the detection of Ransomware-PoC affecting the Raspberry Pi 4 in a few minutes with >90% accuracy.

In 2016, Google proposed Federated Learning (FL) as a novel paradigm to train Machine Learning (ML) models across the participants of a federation while preserving data privacy. Since its birth, Centralized FL (CFL) has been the most used approach, where a central entity aggregates participants' models to create a global one. However, CFL presents limitations such as communication bottlenecks, single point of failure, and reliance on a central server. Decentralized Federated Learning (DFL) addresses these issues by enabling decentralized model aggregation and minimizing dependency on a central entity. Despite these advances, current platforms training DFL models struggle with key issues such as managing heterogeneous federation network topologies. To overcome these challenges, this paper presents Fedstellar, a platform extended from p2pfl library and designed to train FL models in a decentralized, semi-decentralized, and centralized fashion across diverse federations of physical or virtualized devices. The Fedstellar implementation encompasses a web application with an interactive graphical interface, a controller for deploying federations of nodes using physical or virtual devices, and a core deployed on each device which provides the logic needed to train, aggregate, and communicate in the network. The effectiveness of the platform has been demonstrated in two scenarios: a physical deployment involving single-board devices such as Raspberry Pis for detecting cyberattacks, and a virtualized deployment comparing various FL approaches in a controlled environment using MNIST and CIFAR-10 datasets. In both scenarios, Fedstellar demonstrated consistent performance and adaptability, achieving F1 scores of 91%, 98%, and 91.2% using DFL for detecting cyberattacks and classifying MNIST and CIFAR-10, respectively, reducing training time by 32% compared to centralized approaches.

The proliferation of the Internet of Things (IoT) has led to the emergence of crowdsensing applications, where a multitude of interconnected devices collaboratively collect and analyze data. Ensuring the authenticity and integrity of the data collected by these devices is crucial for reliable decision-making and maintaining trust in the system. Traditional authentication methods are often vulnerable to attacks or can be easily duplicated, posing challenges to securing crowdsensing applications. Besides, current solutions leveraging device behavior are mostly focused on device identification, which is a simpler task than authentication. To address these issues, an individual IoT device authentication framework based on hardware behavior fingerprinting and Transformer autoencoders is proposed in this work. This solution leverages the inherent imperfections and variations in IoT device hardware to differentiate between devices with identical specifications. By monitoring and analyzing the behavior of key hardware components, such as the CPU, GPU, RAM, and Storage on devices, unique fingerprints for each device are created. The performance samples are considered as time series data and used to train outlier detection transformer models, one per device and aiming to model its normal data distribution. Then, the framework is validated within a spectrum crowdsensing system leveraging Raspberry Pi devices. After a pool of experiments, the model from each device is able to individually authenticate it between the 45 devices employed for validation. An average True Positive Rate (TPR) of 0.74+-0.13 and an average maximum False Positive Rate (FPR) of 0.06+-0.09 demonstrate the effectiveness of this approach in enhancing authentication, security, and trust in crowdsensing applications.

The aims of this study were twofold: firstly, to compare core stability and knee joint loading between sidestepping experts and nonexperts; secondly, to determine core predictors of knee joint loading. Thirteen handball male players (experts) and fourteen karatekas (nonexperts) performed six unanticipated 45{\textdegree} sidestepping manoeuvers, while trunk and pelvis 3D kinematics as well as ground reaction forces were measured, and peak knee abduction moment (PKAM) was determined. Student t-tests enabled a comparison of both groups and a linear mixed model approach was used to identify PKAM predictors. Sidestepping experts demonstrated significantly lower pelvis rotation towards the new movement direction at the initial contact than nonexperts (4.9{\textdegree} vs. 10.8{\textdegree}) and higher PKAM (0.539 vs. 0.321 Nm/kg-bwt). Trunk medial lean, trunk axial rotation and pelvis anterior tilt at the initial contact predicted PKAM, while trunk axial rotation, pelvis medial lean and posterior ground reaction force predicted PKAM during the weight acceptance phase. Despite higher PKAM, handball players might not be at a higher risk of anterior cruciate ligament injury as the knee joint loading remained at a relatively low level during this sidestepping task. Core stability, in its three dimensions, is a key determinant of knee joint loading.

The rapid expansion of the Internet of Things (IoT) and Edge Computing has presented challenges for centralized Machine and Deep Learning (ML/DL) methods due to the presence of distributed data silos that hold sensitive information. To address concerns regarding data privacy, collaborative and privacy-preserving ML/DL techniques like Federated Learning (FL) have emerged. However, ensuring data privacy and performance alone is insufficient since there is a growing need to establish trust in model predictions. Existing literature has proposed various approaches on trustworthy ML/DL (excluding data privacy), identifying robustness, fairness, explainability, and accountability as important pillars. Nevertheless, further research is required to identify trustworthiness pillars and evaluation metrics specifically relevant to FL models, as well as to develop solutions that can compute the trustworthiness level of FL models. This work examines the existing requirements for evaluating trustworthiness in FL and introduces a comprehensive taxonomy consisting of six pillars (privacy, robustness, fairness, explainability, accountability, and federation), along with over 30 metrics for computing the trustworthiness of FL models. Subsequently, an algorithm named FederatedTrust is designed based on the pillars and metrics identified in the taxonomy to compute the trustworthiness score of FL models. A prototype of FederatedTrust is implemented and integrated into the learning process of FederatedScope, a well-established FL framework. Finally, five experiments are conducted using different configurations of FederatedScope to demonstrate the utility of FederatedTrust in computing the trustworthiness of FL models. Three experiments employ the FEMNIST dataset, and two utilize the N-BaIoT dataset considering a real-world IoT security use case.

We provide an open source framework to experiment with evolutionary algorithms which we call "Experimenting and Learning toolkit for Evolutionary Algorithms (ELEA)". ELEA is browser-based and allows to assemble evolutionary algorithms using drag-and-drop, starting from a number of simple pre-designed examples, making the startup costs for employing the toolkit minimal. The designed examples can be executed and collected data can be displayed graphically. Further features include export of algorithm designs and experimental results as well as multi-threading. With the very intuitive user interface and the short time to get initial experiments going, this tool is especially suitable for explorative analyses of algorithms as well as for the use in classrooms., Comment: You can find a running instance of ELEA as well as its source code at the following URLs: https://elea-toolkit.netlify.app/ https://github.com/HPI-ELEA/elea

Fibers lasers is a field which is typically dominated by rare earth ions as gain material in the core of a silica optical waveguide. Due to their specific emission wavelengths, rare-earth doped fiber lasers are available only at few pre-defined wavelengths. However, Quantum Dots (QDs) are materials, which shows tunable emission with change in size and composition. Due to such tunability, QDs seem to be promising candidates for obtaining fiber lasers at a spectrum of wavelengths which are not possible using rare earth ions. To replace rare earth ions with QDs, it is of paramount importance that QDs show signatures of optical gain. Here, we report synthesis of asymmetric pod-shaped CdSe/CdS QDs, which demonstrate efficient gain through pumping. The intrinsic gain properties of the QDs have been evaluated through Transient Absorption Spectroscopy. Later, the exquisite QDs are used to fabricate specialty fibers from which ASE has been obtained by using CW laser pump at Room Temperatur. Finally, Stability of the emission signal has been by studying photobleaching and controlling the concentration of the QDs.

We report on the development of all-fiber stand-alone Iodine-filled Photonic Microcells demonstrating record absorption contrast at room temperature. The microcell s fiber is made of inhibited coupling guiding hollow-core photonic crystal fibers. The fiber-core loading with Iodine was undertaken at 10-1 - 10-2mbar vapor pressure using a novel gas-manifold based on metallic vacuum parts with ceramic coated inner surfaces for corrosion resistance. The fiber is then sealed on the tips and mounted on FC/APC connectors for better integration with standard fiber components. The stand-alone microcells display Doppler lines with contrasts up to 73% in the 633nm wavelength range, and an insertion loss between 3 to 4dB. Sub-Doppler spectroscopy based on saturable absorption has been carried out to resolve the hyperfine structure of the P(33)6-3 lines at room temperature with a full-width at half maximum of 24MHz on the b4 component with the help of lock-in amplification. Also, we demonstrate distinguishable hyperfine components on the R(39)6-3 line at room temperature without any recourse to signal-to-noise ratio amplification techniques., Comment: 11 pages, 4 figures

In the last years, the number of IoT devices deployed has suffered an undoubted explosion, reaching the scale of billions. However, some new cybersecurity issues have appeared together with this development. Some of these issues are the deployment of unauthorized devices, malicious code modification, malware deployment, or vulnerability exploitation. This fact has motivated the requirement for new device identification mechanisms based on behavior monitoring. Besides, these solutions have recently leveraged Machine and Deep Learning techniques due to the advances in this field and the increase in processing capabilities. In contrast, attackers do not stay stalled and have developed adversarial attacks focused on context modification and ML/DL evaluation evasion applied to IoT device identification solutions. This work explores the performance of hardware behavior-based individual device identification, how it is affected by possible context- and ML/DL-focused attacks, and how its resilience can be improved using defense techniques. In this sense, it proposes an LSTM-CNN architecture based on hardware performance behavior for individual device identification. Then, previous techniques have been compared with the proposed architecture using a hardware performance dataset collected from 45 Raspberry Pi devices running identical software. The LSTM-CNN improves previous solutions achieving a +0.96 average F1-Score and 0.8 minimum TPR for all devices. Afterward, context- and ML/DL-focused adversarial attacks were applied against the previous model to test its robustness. A temperature-based context attack was not able to disrupt the identification. However, some ML/DL state-of-the-art evasion attacks were successful. Finally, adversarial training and model distillation defense techniques are selected to improve the model resilience to evasion attacks, without degrading its performance.

Cybercriminals are moving towards zero-day attacks affecting resource-constrained devices such as single-board computers (SBC). Assuming that perfect security is unrealistic, Moving Target Defense (MTD) is a promising approach to mitigate attacks by dynamically altering target attack surfaces. Still, selecting suitable MTD techniques for zero-day attacks is an open challenge. Reinforcement Learning (RL) could be an effective approach to optimize the MTD selection through trial and error, but the literature fails when i) evaluating the performance of RL and MTD solutions in real-world scenarios, ii) studying whether behavioral fingerprinting is suitable for representing SBC's states, and iii) calculating the consumption of resources in SBC. To improve these limitations, the work at hand proposes an online RL-based framework to learn the correct MTD mechanisms mitigating heterogeneous zero-day attacks in SBC. The framework considers behavioral fingerprinting to represent SBCs' states and RL to learn MTD techniques that mitigate each malicious state. It has been deployed on a real IoT crowdsensing scenario with a Raspberry Pi acting as a spectrum sensor. More in detail, the Raspberry Pi has been infected with different samples of command and control malware, rootkits, and ransomware to later select between four existing MTD techniques. A set of experiments demonstrated the suitability of the framework to learn proper MTD techniques mitigating all attacks (except a harmfulness rootkit) while consuming <1 MB of storage and utilizing <55% CPU and <80% RAM.

In this short paper, we outline the design of Tumult Analytics, a Python framework for differential privacy used at institutions such as the U.S. Census Bureau, the Wikimedia Foundation, or the Internal Revenue Service.

The research enterprise towards achieving high-performance hollow-core photonic crystal fibers has led to impressive advancements in the latest years. Indeed, using this family of fibers becomes nowadays an overarching strategy for building a multitude of optical systems ranging from beam delivery devices to optical sources and sensors. In most applications, an effective single-mode operation is desired and, as such, the fiber microstructure or the light launching setups are typically designed for achieving such a behavior. Alternatively, one can identify the use of large-core multimode hollow-core fibers as a promising avenue for the development of new photonic devices. Thus, in this manuscript, we propose and demonstrate the utilization of a large-core tubular-lattice fiber for accomplishing a speckle-based displacement sensor, which has been built up by inserting and suitably dislocating a single-mode fiber inside the void core of the hollow fiber. The work reported herein encompasses both simulation and experimental studies on the evolution of the multimode intensity distributions within the device as well as the demonstration of a displacement sensor with an estimated resolution of 0.7 {\mu}m. We understand that this investigation identifies a new opportunity for the employment of large-core hollow fibers within the sensing framework hence widening the gamut of applications of this family of fibers.

In recent years, Federated Learning (FL) has gained relevance in training collaborative models without sharing sensitive data. Since its birth, Centralized FL (CFL) has been the most common approach in the literature, where a central entity creates a global model. However, a centralized approach leads to increased latency due to bottlenecks, heightened vulnerability to system failures, and trustworthiness concerns affecting the entity responsible for the global model creation. Decentralized Federated Learning (DFL) emerged to address these concerns by promoting decentralized model aggregation and minimizing reliance on centralized architectures. However, despite the work done in DFL, the literature has not (i) studied the main aspects differentiating DFL and CFL; (ii) analyzed DFL frameworks to create and evaluate new solutions; and (iii) reviewed application scenarios using DFL. Thus, this article identifies and analyzes the main fundamentals of DFL in terms of federation architectures, topologies, communication mechanisms, security approaches, and key performance indicators. Additionally, the paper at hand explores existing mechanisms to optimize critical DFL fundamentals. Then, the most relevant features of the current DFL frameworks are reviewed and compared. After that, it analyzes the most used DFL application scenarios, identifying solutions based on the fundamentals and frameworks previously defined. Finally, the evolution of existing DFL solutions is studied to provide a list of trends, lessons learned, and open challenges.

Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular. However, they are very susceptible to small adversarial perturbations that are carefully crafted to change the network decision. In this work, we build on knowledge distillation ideas and adversarial training in order to build more robust AMC systems. We first outline the importance of the quality of the training data in terms of accuracy and robustness of the model. We then propose to use the Maximum Likelihood function, which could solve the AMC problem in offline settings, to generate better training labels. Those labels teach the model to be uncertain in challenging conditions, which permits to increase the accuracy, as well as the robustness of the model when combined with adversarial training. Interestingly, we observe that this increase in performance transfers to online settings, where the Maximum Likelihood function cannot be used in practice. Overall, this work highlights the potential of learning to be uncertain in difficult scenarios, compared to directly removing label noise.

Federated learning (FL) allows participants to collaboratively train machine and deep learning models while protecting data privacy. However, the FL paradigm still presents drawbacks affecting its trustworthiness since malicious participants could launch adversarial attacks against the training process. Related work has studied the robustness of horizontal FL scenarios under different attacks. However, there is a lack of work evaluating the robustness of decentralized vertical FL and comparing it with horizontal FL architectures affected by adversarial attacks. Thus, this work proposes three decentralized FL architectures, one for horizontal and two for vertical scenarios, namely HoriChain, VertiChain, and VertiComb. These architectures present different neural networks and training protocols suitable for horizontal and vertical scenarios. Then, a decentralized, privacy-preserving, and federated use case with non-IID data to classify handwritten digits is deployed to evaluate the performance of the three architectures. Finally, a set of experiments computes and compares the robustness of the proposed architectures when they are affected by different data poisoning based on image watermarks and gradient poisoning adversarial attacks. The experiments show that even though particular configurations of both attacks can destroy the classification performance of the architectures, HoriChain is the most robust one.

Malware affecting Internet of Things (IoT) devices is rapidly growing due to the relevance of this paradigm in real-world scenarios. Specialized literature has also detected a trend towards multi-purpose malware able to execute different malicious actions such as remote control, data leakage, encryption, or code hiding, among others. Protecting IoT devices against this kind of malware is challenging due to their well-known vulnerabilities and limitation in terms of CPU, memory, and storage. To improve it, the moving target defense (MTD) paradigm was proposed a decade ago and has shown promising results, but there is a lack of IoT MTD solutions dealing with multi-purpose malware. Thus, this work proposes four MTD mechanisms changing IoT devices' network, data, and runtime environment to mitigate multi-purpose malware. Furthermore, it presents a lightweight and IoT-oriented MTD framework to decide what, when, and how the MTD mechanisms are deployed. Finally, the efficiency and effectiveness of the framework and MTD mechanisms are evaluated in a real-world scenario with one IoT spectrum sensor affected by multi-purpose malware.

While optical fibers display excellent performances in the infrared, visible and ultraviolet ranges remain poorly addressed by them. Obtaining better fibers for the short-wavelength range has been restricted, in all fiber optics, by scattering processes. In hollow-core fibers, the scattering loss arises from the core roughness and represents the limiting factor in reducing their loss regardless of the fiber cladding confinement power. To attain fibers performing at short wavelengths, it is paramount developing means to minimize the height variations on the fiber microstructure boundaries. Here, we report on the reduction of the core surface roughness of hollow-core fibers by modifying their fabrication technique. In the novel process proposed herein, counter directional gas fluxes are applied within the fiber holes during fabrication to attain an increased shear rate on its microstructure. The effect of the process on the surface roughness has been quantified by optical profilometry and the results showed that the root-mean-square surface roughness has been reduced from 0.40 nm to 0.15 nm. The improvement in the fiber core surface quality entailed fibers with ultralow loss in the short-wavelength range. We report on fibers with record loss values as low as 50 dB/km at 290 nm, 9.7 dB/km at 369 nm, 5.0 dB/km at 480 nm, and 1.8 dB/km at 719 nm. The results reveal this new approach as a promising path for the development of hollow-core fibers guiding at short wavelengths with loss that can potentially be orders of magnitude lower than the ones achievable with their silica-core counterparts.

Research achievements in hollow-core photonic crystal fibers technology allow ascertaining such fibers as outstanding platforms for delivering high-power laser beams. Indeed, the key property underlying the success of this family of optical fibers for high-power beam delivery is their capability of efficiently transmitting light through empty space with minimal interaction with the fiber microstructure. In this context, here we widen the framework of hollow-core fiber-based beam delivery applications by demonstrating their utilization as promising platforms for Power-over-Fiber systems. Thus, we report on the use of a tubular-lattice hollow-core fiber to deliver a watt-level continuous-wave laser beam onto a photovoltaic converter and activate a representative camera circuit. We believe that the experiments reported herein allow identifying hollow-core fibers as eligible candidates for next-generation Power-over-Fiber devices potentially able to lift the power restrictions of current solid-core fiber-based Power-over-Fiber systems.

In today's computing environment, where Artificial Intelligence (AI) and data processing are moving toward the Internet of Things (IoT) and Edge computing paradigms, benchmarking resource-constrained devices is a critical task to evaluate their suitability and performance. Between the employed devices, Single-Board Computers arise as multi-purpose and affordable systems. The literature has explored Single-Board Computers performance when running high-level benchmarks specialized in particular application scenarios, such as AI or medical applications. However, lower-level benchmarking applications and datasets are needed to enable new Edge-based AI solutions for network, system and service management based on device and component performance, such as individual device identification. Thus, this paper presents LwHBench, a low-level hardware benchmarking application for Single-Board Computers that measures the performance of CPU, GPU, Memory and Storage taking into account the component constraints in these types of devices. LwHBench has been implemented for Raspberry Pi devices and run for 100 days on a set of 45 devices to generate an extensive dataset that allows the usage of AI techniques in scenarios where performance data can help in the device management process. Besides, to demonstrate the inter-scenario capability of the dataset, a series of AI-enabled use cases about device identification and context impact on performance are presented as exploration of the published data. Finally, the benchmark application has been adapted and applied to an agriculture-focused scenario where three RockPro64 devices are present.