AIBearisharXiv – CS AI · Mar 127/10
🧠
Targeted Bit-Flip Attacks on LLM-Based Agents
Researchers have introduced Flip-Agent, the first targeted bit-flip attack framework specifically designed to exploit LLM-based agents by manipulating hardware faults. The attack can manipulate both final outputs and tool invocations in multi-stage AI agent pipelines, revealing critical security vulnerabilities in these systems.