7 papers
SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills
Nizhang Li, Zonghao Ying, Xiangfan Wu +7
External skills extend the capabilities of large language model agents, but also introduce an execution-time attack surface: a skill that appears benign under inspection may reveal…
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
Zhe Liu, Zonghao Ying, Wenxin Zhang +5
Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilit…
TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
Quanchen Zou, Nizhang Li, Wenxin Zhang +4
Text-to-Video (T2V) models have demonstrated remarkable capability in generating temporally coherent videos from natural language prompts, yet they also risk producing unsafe conte…
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Zonghao Ying, Yangguang Shao, Jianle Gan +8
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face…
SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
Zonghao Ying, Moyang Chen, Nizhang Li +6
Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obv…
Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
Junjie Mu, Zonghao Ying, Zhekui Fan +6
Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are d…