New 'SilentDrift' attack targets robotic VLA models

Researchers have developed a novel backdoor attack called SILENTDRIFT that targets Vision-Language-Action (VLA) models used in robotics. The attack exploits a vulnerability in how these models process action sequences, allowing subtle perturbations to accumulate and lead to incorrect execution. SILENTDRIFT achieves a high success rate with minimal poisoning and maintains high performance on clean tasks, making the poisoned trajectories visually indistinguishable from normal operations. AI

IMPACT Highlights critical security vulnerabilities in deployed AI systems, necessitating robust defenses for safety-critical applications.

RANK_REASON The cluster contains a research paper detailing a novel attack method on AI models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Bingxin Xu
• LIBERO
• SILENTDRIFT
• Vision-Language-Action models

• safety
• paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →