Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Zhejiang University（浙江大学）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang Lab（浙江实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Hangzhou Dianzi University（杭州电子科技大学）
Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversarially optimized documents manipulate generated outputs. Existing defenses assume that detecting poisoned evidence prevents harm. We show this assumption is incorrect: models exhibit a monitoring-control gap -- they can detect contradictions in retrieved evidence yet still act on poisoned claims. We introduce the Cordon Principle -- no agent capable of final synthesis may access untrusted natural-language evidence -- and realize it through CORDON-MAS, a compartmentalized framework that enforces this principle architecturally by separating evidence extraction, cross-source audit, and answer synthesis into agents with asymmetric memory privileges. Across five BEIR datasets, CORDON-MAS reduces attack success rate by 92.4\% relative to undefended RAG. This reframes RAG poisoning from a detection problem to an information-flow control problem.
Defending Against Beta Poisoning Attacks in Machine Learning Models
Department of Computer Engineering Acıbadem University Istanbul, Turkiye（计算机工程系 阿克萨德梅大学 伊斯坦布尔，土耳其）；Department of Computer Engineering Koç University Istanbul, Turkiye（计算机工程系 科大学 伊斯坦布尔，土耳其）
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Nanyang Technological University（南洋理工大学）；Hong Kong University of Science and Technology（香港科技大学）；Jinan University（暨南大学）；Sony Research（索尼研究院）；Zhejiang University（浙江大学）；Beijing Institute of Technology（北京理工大学）
Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算高精尖创新中心）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）
Defending Against Poisoning Attacks in Federated Learning with Blockchain
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Imperial College London（帝国理工学院）；UiT The Arctic University of Norway（挪威北极大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
Southern University of Science and Technology（南方科技大学）；University of Science and Technology of China（中国科学技术大学）；University of Birmingham（伯明翰大学）；Zhejiang University（浙江大学）；East China Normal University（华东师范大学）；Alibaba Group（阿里巴巴集团）
