The paper systematically characterizes the fault response of the Intel NCS2 accelerator to electromagnetic fault injection, revealing a major degradation mode that is undetectable by standard inferenc…

This paper demonstrates that Unmanned Aerial Vehicle (UAV) autopilot fail-safe mechanisms are vulnerable to non-invasive voltage glitch fault injection, potentially allowing attackers to suppress crit…

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

The paper proposes MAED, a novel algorithm-level error detection framework that uses mathematical identities to continuously validate non-linear activation functions, achieving high fault detection ra…

This paper proposes a systematic joint workflow combining HARA and TARA to comprehensively identify and analyze risks stemming from inherent limitations of Deep Neural Networks (DNNs) used in autonomo…

The paper introduces a stealthy, scenario-realistic data fabrication attack that subtly manipulates object poses in shared perception data to induce unsafe driving behaviors in connected and autonomou…

This paper demonstrates the successful application of deep learning-assisted differential fault attacks to three lightweight stream ciphers, achieving high fault location identification accuracies and…

This paper systematically audits the safety implications of activation steering vectors, finding that these vectors significantly influence the success rate of jailbreak attacks by overlapping with la…

The paper introduces a novel adversarial attack that uses static, view-dependent camouflage on a vehicle to induce consistent feature drift, causing autonomous systems to predict false, yet plausible,…

FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-a…

The paper proposes a proactive, resilient architecture for autonomous vehicles by integrating redundancy, diversity, and adaptive reconfiguration to defend against various cyber and physical attacks.

The paper proposes a novel hardware extension that enables deterministic, kernel-bypass switching to user-level protection domains upon interrupt arrival, significantly reducing worst-case latency for…

This study investigates how industrial practitioners perceive and manage data leakage in automotive perception systems, finding that leakage control is a socio-technical coordination problem requiring…

The paper proposes a multi-resolution end-to-end deep neural network for autonomous driving that dynamically adjusts input resolution to optimize the critical tradeoff between prediction accuracy and…

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 a novel hardware aging attack that exploits the commutative properties of addition to induce unbalanced stress on AI accelerator transistors, significantly degrading model accurac…

This paper identifies and demonstrates eight novel attack scenarios exploiting the ISO 15765-2 transport protocol over CAN, showing that three can successfully induce denial of diagnostic services in…

This paper investigates Confused Deputy Attacks (CDAs) on AI Accelerators (AIAs) and finds that CDA is feasible on most major vendor AIAs, impacting a vast number of devices.

The paper proposes DAIRE, a lightweight AI model, for highly efficient, real-time detection and classification of various cyberattacks targeting the vulnerable Controller Area Network (CAN) in the Int…

The paper proposes CANGuard, a hybrid CNN-GRU-Attention deep learning model, to accurately detect sophisticated Denial-of-Service and spoofing attacks targeting critical in-vehicle CAN bus networks.