Ke Xu

This paper systematically evaluates Provenance-based Intrusion Detection Systems (PIDSes) in real industrial scenarios, revealing that existing systems struggle with data heterogeneity, advanced attacks, and high false positive rates.

This paper systematically identifies and demonstrates multiple session manipulation attacks against VPN connection tracking frameworks, revealing widespread vulnerabilities in popular VPN services.

The paper introduces AgentWard, a lifecycle-oriented, defense-in-depth architecture designed to systematically secure autonomous AI agents by protecting them across all stages of their operation.

AFL-ICP is a novel specification-driven fuzzing framework that significantly enhances the security testing of industrial control protocols by detecting subtle semantic and logic bugs missed by traditional fuzzers.

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to perform active cross-modal perception.

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundaries across diverse graph connectivity types.