Voice-based Speaker Identification (SI) can be framed as the problem of Closed-Set Speaker Identification (CSSI), recognizing a speaker from a known set, or OSSI, additionally recognizing unknown speakers. Precise and accurate Open-Set Speaker Identification (SI) can enable a variety of applications, ranging from human presence detection to authentication. Existing SI solutions are typically driven by deep learning approaches, which involve computationally demanding models often running in cloud back-ends. Enabling local SI models running directly on resource-constrained embedded devices can enable new use cases while preserving speaker privacy. In this work, we fill this gap and present SPIDER, a lightweight, on-device CSSI and OSSI solution capable of running on the off-the-shelf Nordic nRF52840 and nRF5340 system-on-chip microcontrollers, which feature as little as 256 and 512 kB of RAM, respectively, and 1 MB of flash memory. SPIDER is 16x-67x smaller than currently-available SI models, and yet, the 16x smaller version achieves a comparable accuracy of 94.33 % for CSSI and 91.8% for OSSI. Our evaluation across multiple datasets confirms the viability of performing accurate SI directly on resource-constrained embedded devices using only low-cost microphones. To foster further research and development, we open source our implementation of SPIDER, empowering the community to explore new SI use cases where cloud connectivity or backhaul infrastructure is impractical or undesirable.

Edge computing pushes computation closer to data sources, but it also expands the attack surface on resource-constrained devices. This work explores the deployment of the Lightweight Deep Anomaly Detection for Network Traffic (LDPI) integrated as an isolated service within a virtualization framework that provides security by separation. LDPI, adopting a Deep Learning approach, achieved strong training performance, reaching AUC 0.999 (5-fold mean) across the evaluated packet-window settings (n, l), with high F1 at conservative operating points. We deploy LDPI on a laptop-class edge node and evaluate its overhead and performance in two scenarios: (i) comparing it with representative signature-based IDSes (Suricata and Snort) deployed on the same framework under identical workloads, and (ii) while detecting network flooding attacks.

Unmanned Aerial Vehicles (UAVs), or drones, are emblematic examples of cyber-physical systems where computational components and physical processes integrate to enable autonomous navigation. UAVs rely heavily on sensors such as Inertial Measurement Units (IMU) and Global Positioning System (GPS) for accurate environmental awareness and control. However, the trust placed in these sensors makes UAVs vulnerable to adversarial attacks that compromise the UAV’s operational integrity. While prior work focuses on detecting attacks against specific sensors, there remains a critical gap in performing Root Cause Analysis (RCA) to determine which component failed and why – especially under ambiguous or conflicting sensor reports. To address this gap, we propose SoundBoost, a novel RCA framework that leverages the UAV’s acoustic side-channel (i.e., sound) to diagnose navigation failures and attribute them to specific sensor compromises. While SoundBoost detects attacks by validating GPS and IMU sensor data, it focuses on post-incident diagnosis. SoundBoost conducts post-incident RCA by extracting robust acoustic signatures and using machine learning to cross-validate reported kinematics against physical behavior. We deploy SoundBoost on a UAV and evaluate it under real-world GPS spoofing attacks and synthesized IMU biasing attacks. SoundBoost achieves 100% true positive rate for IMU attacks and over 80% for GPS spoofing, outperforming the state-of-the-art by 21% – demonstrating its effectiveness as a practical forensic tool for sensor attack RCA.

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting excessive variance among inliers or failing to preserve the diversity of outliers. We begin by analyzing the challenges of representation learning for anomaly detection and identify three essential properties for the pretext task: (1) compact clustering of inliers, (2) strong separation between inliers and anomalies, and (3) preservation of diversity among synthetic outliers. Building on this, we propose a contrastive objective that systematically integrates them into the loss design, enabling effective anomaly representation learning without relying on explicit anomaly labels. We extend this framework with a patch-based learning and evaluation strategy specifically designed to improve the detection of localized anomalies in industrial settings. Our approach demonstrates significantly faster convergence and improved performance compared to standard contrastive methods. It matches or surpasses anomaly detection methods on both semantic and industrial benchmarks, including methods that rely on discriminative training or explicit anomaly labels.

Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Their ability to produce both physically plausible and differentiable models of scenes are key ingredient needed to produce physically plausible adversarial attacks on DNNs. However, the adversarial machine learning community has yet to fully explore these capabilities, partly due to differing attack goals (e.g., misclassification, misdetection) and a wide range of possible scene manipulations used to achieve them (e.g., alter texture, mesh). This survey contributes a framework that unifies diverse goals and tasks, facilitating easy comparison of existing work, identifying research gaps, and highlighting future directions—ranging from expanding attack goals and tasks to account for new modalities, state-of-the-art models, tools, and pipelines, to underscoring the importance of studying real-world threats in complex scenes.

Modern autopilot systems are prone to sensor attacks that can jeopardize flight safety. To mitigate this risk, we proposed a modular solution: the secure safety filter, which extends the well-established control barrier function (CBF)-based safety filter to account for, and mitigate, sensor attacks. This module consists of a secure state reconstructor (which generates plausible states) and a safety filter (which computes the safe control input that is closest to the nominal one). Differing from existing work focusing on linear, noise-free systems, the proposed secure safety filter handles bounded measurement noise and, by leveraging reduced-order model techniques, is applicable to the nonlinear dynamics of drones. Software-in-the-loop simulations and drone hardware experiments demonstrate the effectiveness of the secure safety filter in rendering the system safe in the presence of sensor attacks.

In an era where digital security is paramount, the concept of Trusted Execution Environments (TEEs) is crucial for safeguarding sensitive data within computing systems. This paper introduces an implementation of seL4 as a secure operating system in a TEE on RISC-V hardware. We address integration challenges, offering insights for future secure system designs. A comprehensive performance evaluation of the seL4-based TEE shows enhanced security and operational efficiency. This includes assessments of the Linux Rich Execution Environment’s (REE) performance and analyses of essential TEE services: Random Number Generation, Key Pair Generation, and Digital Signing Operations. Our deployment on the PolarFire SoC Icicle kit demonstrates practicality and viability in a real-world environment. This research contributes to trusted computing area by merging seL4’s robust microkernel architecture with RISC-V’s open-source flexibility, fostering secure, efficient, and adaptable computing solutions.

Over the last years, several machine learning techniques have been proposed for the condition monitoring of physical assets based on audio. As a result, adversaries have been trying to circumvent the reliability of deployed systems, typically through the generation of maliciously altered audio samples that are subsequently introduced as input by the model. However, altering the input in production settings is not always feasible, on the contrary, samples are often collected through a microphone, significantly increasing the attack execution effort. In this paper, we propose a realistic generative adversarial network attack for an audio-based condition monitoring system. We first train a generator and a discriminator with a joint objective of generating audio samples corresponding to the difference between the two classes, e.g., normal and faulty. Additionally, we test our approach by overlapping our generated audio on the samples collected by the microphone. Our main goal is the proposal of a GAN-based attack capable of generating audio samples that when overlaid with the original microphone-captured audio may induce misclassification given a target class. Experiments performed through our captured audio dataset from normal and broken unmanned aerial vehicle propellers show that the proposed attack achieved a mean success rate of 40%, decreasing the F-measure concerning random noise by 13.3%, 20%, and 37.8% for ResNet-18, AlexNet, and DenseNet-169 models, respectively.

Voice is a convenient and popular way to interact with our digital world. Besides translating speech to text, it is also possible to identify speakers based on their voice profile. To date, speaker identification has predominantly been limited to high-performance computational platforms owing to the intricate nature of the underlying algorithms. In this work, we demonstrate that it is possible to reduce model complexity by the required factor of ~10, such that speaker identification can be made feasible for embedded devices with limited resources. We further describe and discuss novel use cases, such as voice-based presence detection and authentication, that become feasible on these class of devices.

As the number of heterogenous IP-connected devices and traffic volume increase, so does the potential for security breaches. The undetected exploitation of these breaches can bring severe cybersecurity and privacy risks. Anomaly-based Intrusion Detection Systems (IDSs) play an essential role in network security. In this paper, we present a practical unsupervised anomaly-based deep learning detection system called ARCADE (Adversarially Regularized Convolutional Autoencoder for unsupervised network anomaly DEtection). With a convolutional Autoencoder (AE), ARCADE automatically builds a profile of the normal traffic using a subset of raw bytes of a few initial packets of network flows so that potential network anomalies and intrusions can be efficiently detected before they cause more damage to the network. ARCADE is trained exclusively on normal traffic. An adversarial training strategy is proposed to regularize and decrease the AE’s capabilities to reconstruct network flows that are out-of-the-normal distribution, thereby improving its anomaly detection capabilities. The proposed approach is more effective than state-of-the-art deep learning approaches for network anomaly detection. Even when examining only two initial packets of a network flow, ARCADE can effectively detect malware infection and network attacks. ARCADE presents 20 times fewer parameters than baselines, achieving significantly faster detection speed and reaction time.

Jamming attacks, as a form of a denial-of-service attack, significantly degrade the performance of wireless communication systems and can lead to significant overhead in terms of re-transmissions and increased power consumption. In this work, we demonstrate the optimal jamming waveform in internet-of-things (IoT) networks. In particular, we present the analytical bit error rate (BER) of the system under attack by employing two common jamming waveforms: Gaussian noise, and digitally modulated. Then, we validate this analysis with the aid of simulations using the MATLAB WLAN toolbox. Obtained analytical and simulation results, demonstrated system performance degradation under jamming attacks. The simulation results agree with the analytical results in terms of determining the effective jamming waveform. Furthermore, the simulation results depict a 100% PER when the jamming to signal ratio (JSR) is OdB for both QPSK modulated and Gaussian noise waveforms which corroborates with the findings in the literature.

UAVs are increasingly appearing in swarms or formations to leverage cooperative behavior, forming flying ad hoc networks. These UAV-enabled networks can meet several complex mission requirements and are seen as a potential enabler for many of the emerging use-cases in future communication networks. Such networks, however, are characterized by a highly dynamic and mobile environment with no guarantee of a central network infrastructure which can cause both connectivity and security issues. While wireless mesh networks are envisioned as a solution for such scenarios, these networks come with their own challenges and security vulnerabilities. In this paper, we analyze the key security and resilience issues resulting from the application of wireless mesh networks within UAV swarms. Specifically, we highlight the main challenges of applying current mesh technologies within the domain of UAV swarms and expose existing vulnerabilities across the communication stack. Based on this analysis, we present a security-focused architecture for UAV mesh communications. Finally, from the identification of these vulnerabilities, we discuss research opportunities posed by the unique challenges of UAV swarm connectivity.

Traditional planning and scheduling techniques still hold important roles in modern smart scheduling systems. Realistic features present in modern manufacturing systems need to be incorporated into these techniques. The real-world problem addressed here is an extension of flexible job shop scheduling problem and is issued from the modern printing and boarding industry. The precedence between operations of each job is given by an arbitrary directed acyclic graph rather than a linear order. In this paper, we extend the traditional FJSP solutions representation to address the parallel operations. We propose an imperialist competitive algorithm for the problem. Several instances are used for the experiments and the results show that, for the considered instances, the proposed algorithm is faster and found better or equal solutions compared to the state-of-the-art algorithms.

During the past few years, with the fast development and proliferation of the Internet of Things (IoT), many application areas have started to exploit this new computing paradigm. The number of active computing devices has been growing at a rapid pace in IoT environments around the world. Consequently, a mechanism to deal with this different devices has become necessary. Middleware systems solutions for IoT have been developed in both research and industrial environments to supply this need. However, decision analytics remain a critical challenge. In this work we present the Decision Support IoT Framework composed of COBASEN, an IoT search engine to address the research challenge regarding the discovery and selection of IoT devices when large number of devices with overlapping and sometimes redundant functionality are available in IoT middleware systems, and DMS, a rule-based reasoner engine allowing to set up computational analytics on device data when it is still in motion, extracting valuable information from it for automated decision making. DMS uses Complex Event Processing to analyze and react over streaming data, allowing for example, to trigger an actuator when a specific error or condition appears in the stream. The main goal of this work is to highlight the importance of a decision support system for decision analytics in the IoT paradigm. We developed a system which implements DMS concepts. However, for preliminarily tests, we made a functional evaluation of both systems in terms of performance. Our initial findings suggest that the Decision Support IoT Framework provides important approaches that facilitate the development of IoT applications, and provides a new way to see how the business rules and decision-making will be made towards the Internet of Things.

During the past few years, with the fast development and proliferation of the Internet of Things (IoT), many application areas have started to exploit this new computing paradigm. An interesting use of IoT is in the Industrial field, which has resulted in a new business concept called IIoT (Industrial Internet of Things). Another important fact is the number of active computing devices has been growing at a rapid pace in IoT environments around the world. Consequently, a mechanism to deal with this different devices has become necessary. Middleware systems solutions for IoT have been developed in both research and industrial environments to supply this need. However, discover, search, select, and interact with devices remain a critical challenge. In this paper we present COBASEN, a software framework composed of a Context Module and a Search Engine to address the research challenge regarding the discovery and interaction with IoT devices when large number of devices with overlapping and sometimes redundant functionality are available in IoT middleware systems. The search engine of the COBASEN operates based on the semantic characteristics of the devices, which is provided by the context module, and that helps users in their interactions with desired devices. The main goal of this work is to highlight the importance of a context-based search engine in the IoT paradigm and to provide a solution that addresses the proper management of search and usage in IoT middleware environments. We developed a tool that implements all COBASEN concepts. However, for preliminarily tests, we made a functional evaluation of the search engine in terms of performance for indexing and querying response time. Our initial findings suggest that COBASEN provides important approaches that facilitate the development of IIoT applications, which based on the COBASEN systems support, may perform essential roles to improve industrial processes.

In the last years a new computing paradigm called Internet of Things (IoT) has been gaining more attention. This paradigm has become popular by embedding mobile network and processing capability into a wide range of physical computing devices used in everyday life of many people. An important part that composes the IoT is the middleware, which is a system that abstracts the management of physical devices and provides services based on the information of these devices. Context-aware is an important feature of IoT middleware systems. This feature allows to discover, understand, and store relevant information related to devices and their respective events. In this sense, this work aims to present an ongoing system that has been developed to provide services of contextualized information about IoT devices in heterogeneous environments.