本人现任验室智能安全团队负责人，主要从事智能算法测评、智能体安全等方向研究工作。团队聚焦高风险领域，围绕人工智能技术在算法模型、生成内容、代理行为等维度风险，开展安全测评、风险检测与防护技术研究。

   

083500-软件工程

人工智能安全、智能算法测试

2015-09--2021-06   中国科学院大学   工学博士
2011-09--2015-06   武汉大学   工学学士

2023-10~现在, 中国科学院软件研究所, 副研究员
2021-07~2023-09,中国科学院软件研究所, 特别研究助理

VuLRTEx: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report, TOSEM (CCF-A), 通讯作者 

All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction, ACL2026 (CCF-A), 通讯作者 

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning, Findings of the Association for Computational Linguistics: ACL 2026, 通讯作者

Mimickingthe Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System, ACL2025 (CCF-A), 通讯作者, SAC Highlights Awards

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems, Findings of the Association for Computational Linguistics: EMNLP 2025, 通讯作者

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems, Findings of the Association for Computational Linguistics: EMNLP 2025, 通讯作者

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection, NAACL 2026, (CCF-B), 通讯作者

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing, TOSEM (CCF-A), 通讯作者

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement, EMNLP2025 (CCF-B), 通讯作者

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues, ACL24 (CCF-A), 第一作者

Cross-Domain Requirements Linking via Adversarial-based Domain Adaptation,ICSE 2023 (CCF-A), 通讯作者

Context-aware Bug Reproduction for Mobile Apps, ICSE 2023 (CCF-A)

Putting Them under Microscope: A Fine-grained Approach for Detecting Redundant Test Cases in Natural Language, ESEC/FSE 2022 (CCF-A),第一作者

Automated Data Function Extraction from Textual Requirements by Leveraging Semi-Supervised CRF and Language Model.  Information and Software Technology 2022 (CCF-B), 第一作者

A Deep Multitask Learning Approach for Requirements Discovery and Annotation from Open Forum, ASE 2020 (CCF-A), 第一作者

Automated Extraction of Requirement Entities by Leveraging LSTM-CRF and Transfer Learning, ICSME 2020 (CCF-B), 第一作者

Learning to Extract Transaction Function from Requirements: An Industrial Case on Financial Software, ESEC/FSE 2020 (CCF-A), 第二作者

Detection of Hidden Feature Requests from Massive Chat Messages via Deep Siamese Network, ICSE 2020 (CCF-A), 第三作者

A Deep Context-wise Method for Coreference Detection in Natural Language Requirements, RE 2020 (CCF-B)，第三作者

Are All Duplicates Value-Neutral? An Empirical Analysis of Duplicate Issue Reports, QRS (CCF-C), 第一作者

Images Don’t Lie: Duplicate Crowdtesting Reports Detection with Screenshot Information. Information and Software Technology 2018 (CCF-B)，第二作者