Konrad Rieck

This paper analyzes the security of LLM-based autonomous agents by drawing parallels to operating system security, finding that while some vulnerabilities are inherent, many can be mitigated using established OS techniques.

This paper identifies three core weaknesses—benchmark vulnerabilities, temporal staleness, and runtime uncertainty—that undermine current AI agent security evaluations and proposes directions for building more robust testing frameworks.

This paper introduces a fingerprinting method that exploits subtle numerical deviations in the inference system components (like the engine or hardware) to reliably identify the specific components used to run a Large Language Model.