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

The paper analyzes existing hardware Trojan datasets to demonstrate that standard cell libraries can be systematically exploited to create visually undetectable, stealthy hardware Trojans, exemplified…

The paper introduces AutoMIA, a novel framework that uses LLM agents to automate the discovery and implementation of Membership Inference Attacks (MIAs), achieving state-of-the-art performance by syst…

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

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…

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

The paper introduces PINSIGHT, a novel methodology that rigorously assesses Wi-Fi PIN code inference attacks by separating environmental effects from typing effects, concluding that current state-of-t…

This paper investigates the vulnerability of machine learning-based fault detection and localization systems in Cyber-Physical Systems (CPS) to backdoor attacks, demonstrating that such attacks are su…

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving f…

This survey reviews the integration of AI and LLMs into hardware security verification, demonstrating its potential to automate complex stages while stressing the necessity of grounding AI outputs in…

This paper systematically investigates the vulnerability of near-field mmWave imaging to physical waveform-domain adversarial attacks, demonstrating that while deep learning algorithms show higher rob…

The paper demonstrates that the Brazilian e-Voting Machine interface generates a simple and highly distinctive electromagnetic spectral signature, raising significant concerns about its susceptibility…

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…

The paper proposes a novel Adversarial Attenuation Patch (AAP) method, which is a physically realizable and stealthy adversarial attack designed to degrade SAR target detection performance.

The paper compares two sparse autoencoder architectures, finding that Differential SAEs (Diff-SAE) significantly outperform Crosscoders in isolating backdoor-related features in language models.

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 identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

This paper addresses the security vulnerability of OFDM-based Physical Layer Authentication (PLA) when channel fading exhibits correlation, proposing a new attack model and a measurable guideline to d…