3 papers
cs.CR2026
Right Facts, Wrong Rule: Scope-Transfer Poisoning of Retrieval-Augmented Generation
Kaisheng Fan, Yishu Gao, Xunzhu Tang +2
Retrieval-augmented generation (RAG) systems use external documents for facts and rules that guide answers. We study rule-scope misapplication, where a rule valid within its docume…
cs.CR2026
BMA: Backchain Memory Attacks Create Unauthorized Control Paths in LLM Agents
Kaisheng Fan, Yishu Gao, Xunzhu Tang +2
Persistent memory enables LLM agents to reuse prior experience, but creates a new security boundary: what an agent may remember is not what it should act on. We expose an unauthori…
cs.CR2026
Defusing the Trigger: Tail-Risk-Informed Attention Rebalancing for LLM Backdoor Mitigation
Kaisheng Fan, Yishu Gao, Xunzhu Tang +2
Backdoored large language models (LLMs) exhibit attacker-specified behavior at inference time while retaining normal performance on benign inputs. Existing mitigations often requir…