4 papers
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
Shihao Weng, Yang Feng, Xiaofei Xie +1
Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user r…
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
Shihao Weng, Yang Feng, Jinrui Zhang +3
Large Language Model (LLM) agents are increasingly deployed as task-oriented software systems that use runtime context to decide and act on behalf of users. This delegation model m…
Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges
Shihao Weng, Yang Feng, Xiaofei Xie
LLM-as-a-Judge pipelines have become the de facto evaluator for agent safety, yet existing benchmarks treat their verdicts as ground-truth proxies without checking whether the verd…
AtPatch: Debugging Transformers via Hot-Fixing Over-Attention
Shihao Weng, Yang Feng, Jincheng Li +3
Transformer-based deep neural networks (DNNs) affected by backdoor attacks and unfairness typically exhibit anomalous attention patterns, leading to over-attend to backdoor trigger…