Ahmad-Reza Sadeghi

The paper proposes HammerWatch, a novel remote attestation protocol that enables external verifiers to detect hardware-induced disturbances, specifically Rowhammer-like attacks, by analyzing memory-level evidence.

Walma is a machine learning framework that uses memory snapshot classification to detect memory corruption and external tampering in WebAssembly, demonstrating practical feasibility with low overhead.

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.