7 papers
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu +2
By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving genera…
False Reality: Uncovering Sensor-induced Human-VR Interaction Vulnerability
Yancheng Jiang, Yan Jiang, Ruochen Zhou +3
Virtual Reality (VR) techniques, serving as the bridge between the real and virtual worlds, have boomed and are widely used in manufacturing, remote healthcare, gaming, etc. Specif…
Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt
Yujie Gu, Richeng Jin, Xiaoyu Ji +2
Large Language Models (LLMs) have achieved remarkable performance and received significant research interest. The enormous computational demands, however, hinder the local deployme…
Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
Xuancun Lu, Jiaxiang Chen, Shilin Xiao +7
Vision-Language-Action (VLA) models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual s…
SoK: Understanding the Fundamentals and Implications of Sensor Out-of-band Vulnerabilities
Shilin Xiao, Wenjun Zhu, Yan Jiang +5
Sensors are fundamental to cyber-physical systems (CPS), enabling perception and control by transducing physical stimuli into digital measurements. However, despite growing researc…
POEX: Towards Policy Executable Jailbreak Attacks Against the LLM-based Robots
Xuancun Lu, Zhengxian Huang, Xinfeng Li +3
The integration of LLMs into robots has witnessed significant growth, where LLMs can convert instructions into executable robot policies. However, the inherent vulnerability of LLM…