Qingsong Peng

SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well-studied, Bit-Flip Attacks (BFAs)—which exploit hardware vulnerabilities to corrupt model paramete…