11 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…
What Does It Mean to Forget a Person? Individual-Level Unlearning in Vision-Language Models
Xiongtao Sun, Hui Li, Tiantong Wu +3
Erasing individual identities from Vision-Language Models (VLMs) is uniquely challenging because personal data is entangled across modalities rather than stored as isolated attribu…
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
Fuyao Zhang, Xuan Wang, Zherui Li +3
Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing app…
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…
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…
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
Che Wang, Fuyao Zhang, Jiaming Zhang +6
Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existi…
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…
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Fuyao Zhang, Xinyu Yan, Tiantong Wu +7
Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning while preserving data privacy. However, while…
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…