This paper systematically analyzes 48 studies on perception attacks against autonomous vehicles, revealing that the increasing reliance on multi-sensor fusion creates new, complex vulnerabilities that…

The paper introduces a threat-oriented digital twinning methodology to enable reproducible and controllable cybersecurity evaluation of autonomous platforms, overcoming limitations in accessing real-w…

The paper proposes an uncertainty-aware, decentralized fusion layer for multi-UAV systems that significantly improves 3D localization robustness by incorporating neighbor constraints and handling faul…

The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to ac…

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) ar…

This paper evaluates the physical transfer of adversarial patches against aerial vehicle detectors, finding that while digitally optimized patches can be highly effective, their real-world robustness…

The paper demonstrates a coordinated, cross-modal spoofing attack that successfully deceives state-of-the-art multi-sensor fusion systems in autonomous vehicles by making multiple sensors agree on a f…

EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

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,…

FLORO is a multimodal geospatial foundation model that learns transferable remote sensing representations from a small, diverse corpus, achieving strong performance across various sensor types and res…

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…

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.

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

DeepIPCv3 is a novel multi-modal framework that fuses LiDAR and DVS event streams using cross-modal attention to achieve state-of-the-art, highly reactive avoidance maneuvers for sudden pedestrian cro…

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

This paper proposes a cloud-edge-end collaborative defense framework to secure UAV swarms against various threats like GPS spoofing and multi-hop intrusions, demonstrating its effectiveness through ex…

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.

The paper proposes a decentralized, privacy-aware framework enabling smart cameras to autonomously coordinate their view coverage in public spaces while explicitly excluding sensitive regions, achievi…

The paper introduces Glass Box, a runtime constitutional AI verification layer designed to ensure the safety and adherence to physical laws for autonomous AI systems operating in orbital data centers.