Han Xu

发表论文 18 篇 · 总被引 869 次 · h-index 12

代表论文

• The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) (2024 · Annual Meeting of the Association for Computational Linguistics · 被引 246)
• Red-Teaming LLM Multi-Agent Systems via Communication Attacks (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 131)
• A Robust Semantics-based Watermark for Large Language Model against Paraphrasing (2023 · NAACL-HLT · 被引 103)
• Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (2024 · Conference on Empirical Methods in Natural Language Processing · 被引 76)
• Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention (2024 · European Conference on Computer Vision · 被引 69)
• Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2024 · Conference on Empirical Methods in Natural Language Processing · 被引 69)