collaborators

6 papers

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…

cs.LG2026

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…

cs.CR2026

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…

cs.CR2026

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…