5 papers · 1 filter
CU in RAG: Compositional Concept Unlearning in Retrieval-Augmented Generation
Yiyang Duan, Fan Wu, Tiantong Wu +5
Retrieval-augmented generation can expose unwanted concepts through retrieved evidence even when the generator is moderated. We study query-side concept suppression with a fixed en…
SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains
Fuyao Zhang, Jiaming Zhang, Che Wang +7
Computer-use agents~(CUAs) have transformed large language models into persistent execution systems capable of generating, storing, and reusing artifacts like skills and memory ent…
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li +14
Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technica…
CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents
Blaise Delattre, Cong Wang, Yang Cao
Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates generally authorize the observed…
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
Blaise Delattre, Hengyu Wu, Paul Caillon +2
Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in i…