TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reasoning mechanisms remains largely unexplored. In this paper, we show that CoT reasoning introduces a novel attack vector for targeted behavior hijacking--for example, causing a robot to mistakenly deliver a knife to a person instead of an apple--witho
Record details
Published: 24 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
AgentWall: A Runtime Safety Layer for Local AI Agents
arXiv · 24 March 2026
BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents
arXiv · 25 March 2026
Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
arXiv · 25 March 2026
A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems
arXiv · 23 March 2026
From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies
arXiv · 26 March 2026
Emergent Formal Verification: How an Autonomous AI Ecosystem Independently Discovered SMT-Based Safety Across Six Domains
arXiv · 22 March 2026
How to cite this record
ethics.ai (24 March 2026), “TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches,” evidence record 6812, https://ethics.ai/record/6812 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.