4 papers
WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents
Lin-Fa Lee, YI-YU Chang, Kuo-Hui Yeh
The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser secur…
QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation
Lin-Fa Lee, Yi-Yu Chang, Kuo-Hei Yeh
Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation. To constrain additional model storage overhead, several ex…
On the Security Implications of PQC in TLS: Handshake Exhaustion and IDS Degradation
Lin-Fa Lee, Yi-Yu Chang, Chia-Mu Yu +1
Post-Quantum Cryptography (PQC) is increasingly being integrated into TLS 1.3 to enhance resilience against quantum-enabled attacks. However, the additional computational and commu…
WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents
Lin-Fa Lee, Yi-Yu Chang, Chia-Mu Yu +1
WebMCP is a newly emerging protocol that enables websites to expose tools directly to AI agents, bypassing traditional user interfaces and introducing new security risks. The dynam…