The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper introduces BFIAttack, a novel attack that exploits Beamforming Feedback Information (BFI) to reconstruct a user's Channel State Information (CSI), thereby compromising Wi-Fi physical-layer s…

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…

This paper investigates a novel physical backdoor attack against Deep Automatic Modulation Classifiers (AMC) in wireless communications, demonstrating that an adversary using Explainable AI (XAI) can…

This paper proposes a lightweight, multi-layer Machine Learning-based security framework for Industrial IoT (IIoT) to enhance trust convergence and detect advanced threats.

The paper proposes ExAI5G, a logic-based explainable AI framework that integrates a Transformer-based IDS with XAI techniques to provide highly accurate and transparent intrusion detection for 5G netw…

The paper demonstrates that simpler, shallower Deep Neural Network architectures with reduced features and ReLU activations can inherently improve the robustness of ML-NIDS against gradient-based adve…

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…

This paper surveys information-theoretic approaches to secure Integrated Sensing and Communication (ISAC), providing a comprehensive review of models, security formulations, and fundamental limits.

The paper introduces Devilray, a comprehensive adversarial model that systematically tests the realistic operational space of fake base stations, revealing significant blind spots in existing detectio…

This paper proposes a physical backdoor attack against deep learning modulation classifiers, utilizing power amplifier non-linear distortions as physical triggers to achieve high attack success rates.

This paper proposes a federated learning framework using FedAvg to detect RF jamming attacks in 5G networks directly from over-the-air IQ samples, achieving high accuracy while maintaining user data p…

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functi…

This paper demonstrates that LLM cascade systems, designed for efficiency, are vulnerable to targeted adversarial attacks that simultaneously degrade both performance and cost-efficiency.

The paper proposes DA-GC, a certified causal attribution framework that accurately identifies cross-slice attack origins in 6G networks under strict real-time latency constraints by systematically mod…

The paper introduces SpikeWFM, a novel hybrid architecture combining spiking neural networks (SNNs) and transformers, which significantly improves the robustness and accuracy of wireless foundation mo…

The paper introduces DECKER, a domain-invariant framework that significantly improves cross-keyboard keystroke inference by normalizing device variations and leveraging linguistic context, demonstrati…

The paper proposes a two-stage robust aggregation framework to detect and mitigate stealthy backdoor attacks in Over-the-air Federated Learning (OTA-FL) systems, effectively maintaining main-task accu…

This paper models PIN entry as a stochastic communication channel, proposing a probabilistic inference framework to quantify reliability loss and QoS degradation caused by partial information leakage.