See-Kiong Ng

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.

The paper proposes DareU, a novel LLM unlearning framework that optimizes unlearning by zeroing out data attribution scores instead of maximizing prediction loss, achieving effective unlearning while maintaining model utility.

FineVerify introduces a fine-grained self-verification framework that improves agentic search by decomposing complex questions into verifiable sub-questions, leading to significant accuracy gains over standard scaling methods.