7 papers
Forgetting Similar Samples: Can Machine Unlearning Do it Better?
Heng Xu, Tianqing Zhu, Dayong Ye +3
Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extens…
VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference
Minfeng Qi, Dongyang He, Qin Wang +1
Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are i…
The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
Zijie Xu, Minfeng Qi, Shiqing Wu +4
Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically va…
Collaborative Text-to-Image Generation via Multi-Agent Reinforcement Learning and Semantic Fusion
Jiabao Shi, Minfeng Qi, Lefeng Zhang +5
Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose…
Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
Minfeng Qi, Tianqing Zhu, Lefeng Zhang +2
Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale rem…
Vertical Federated Unlearning via Backdoor Certification
Mengde Han, Tianqing Zhu, Lefeng Zhang +2
Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method…