53 citations · 53 across the 5 of their papers we have counts for
6 papers
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Lingqi Jiang, Jialuo Chen, Jianan Ma +8
Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and inspect durin…
Mitigating Proxy-Induced Traffic Drift in Website Fingerprinting via Model-Agnostic Traffic Tailoring
Linxiao Yu, Tianyu Cui, Xinhao Deng +4
Website fingerprinting (WF) based on deep learning can effectively identify websites from encrypted traffic. However, users often rely on proxy protocols to bypass censorship, and…
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Jialuo Chen, Lingqi Jiang, Xinhao Deng +7
Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a…
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin, Xinhao Deng, Qingming Li +12
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…
EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
Yunqi Liu, Tong Niu, Zitong Wang +4
As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic inte…
Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
Yuqi Qing, Qilei Yin, Xinhao Deng +6
Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a su…