6 papers
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
Shanghao Shi, Xiao Wang, Chaoyu Zhang +6
The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injecti…
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
Shanghao Shi, Chaoyu Zhang, Heng Jin +6
Federated learning (FL) enables multiple parties to collaboratively fine-tune language models for domain-specific tasks without sharing raw data. Since full model fine-tuning is of…
AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
Hao Li, Ruoyao Wen, Shanghao Shi +3
AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes…
Low Rank Adaptation for Adversarial Perturbation
Han Liu, Shanghao Shi, Yevgeniy Vorobeychik +2
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large…
Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
Peichun Hua, Hao Li, Shanghao Shi +2
Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and effi…
TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
Zhen Guo, Shanghao Shi, Hao Li +3
The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, th…