9 papers
VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
Yurong Hao, Wen Zhou, Guowei Guan +3
Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents, whose semantic states are dy…
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…
XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition
Gong Zhiren, Tiantong Wu, Jiaming Zhang +9
Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characteri…
FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence
Xinyu Yan, Boyang Chen, Jiaming Zhang +12
Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to real-world claims, creating new challenges for verifying visual evidence.…
MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
Tiantong Wang, Xinyu Yan, Tiantong Wu +3
Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. T…
VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
Guowei Guan, Yurong Hao, Jiaming Zhang +6
Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal fusion. We find that while cross-mod…
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
Fuyao Zhang, Jiaming Zhang, Che Wang +6
The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information…
Spattack: Subgroup Poisoning Attacks on Federated Recommender Systems
Bo Yan, Yurong Hao, Dingqi Liu +5
Federated recommender systems (FedRec) have emerged as a promising approach to provide personalized recommendations while protecting user privacy. However, recent studies have show…
Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
Fuyao Zhang, Wenjie Li, Yurong Hao +3
Federated Unlearning (FU) has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearni…