Kwok-Yan Lam

The paper proposes CAAP, a capture-aware adversarial patch framework, demonstrating that deep palmprint recognition systems remain vulnerable to physically realizable attacks despite existing defenses.

This paper addresses the operational challenge of adopting Post-Quantum Cryptography (PQC) in complex financial TLS environments by presenting a methodology to automatically profile and normalize cryptographic configurations across heterogeneous infrastructure.

MemMorph introduces a novel memory poisoning attack that biases LLM agent tool selection by injecting crafted records into the agent's long-term memory, achieving high success rates even against modern defenses.