Jizhong Han

发表论文 102 篇 · 总被引 763 次 · h-index 14

代表论文

• Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills (2026 · arXiv.org · 被引 6)
• Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing (2026 · arXiv.org · 被引 6)
• RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents (2026 · arXiv.org · 被引 4)
• DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy (2025 · International Conference on Computer Supported Cooperative Work in Design · 被引 3)
• A Cognitive Distribution and Behavior-Consistent Framework for Black-Box Attacks on Recommender Systems (2026 · International Conference on Database Systems for Advanced Applications · 被引 1)
• FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing (2026 · Annual Meeting of the Association for Computational Linguistics · 被引 1)