Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

Haibo Jin, Peiyan Zhang, Man Luo, Haohan Wang

The 39th Conference on Neural Information Processing Systems (NeurIPS’25)

PDF / Code

Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation

Jun Zhuang, Haibo Jin, Ye Zhang, Zhengjian Kang, Wenbin Zhang, Gaby G Dagher, Haohan Wang

The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP’25)

PDF

Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

Peiyan Zhang, Haibo Jin, Leyang Hu, Xinnuo Li, Liying Kang, Man Luo, Yangqiu Song, Haohan Wang

The 42nd International Conference on Machine Learning (ICML’25)

PDF / Code

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

Haibo Jin, Andy Zhou, Joe D Menke, Haohan Wang

The 38th Conference on Neural Information Processing Systems (NeurIPS’24)

PDF / Code

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing

Haibo Jin, Ruoxi Chen, Jinyin Chen, Haibin Zheng, Yang Zhang, Haohan Wang

The 18th European Conference on Computer Vision (ECCV’24)

PDF / Code

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models

Ruoxi Chen, Haibo Jin, Yixin Liu, Jinyin Chen, Haohan Wang, Lichao Sun

The 18th European Conference on Computer Vision (ECCV’24)

PDF / Code

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

Haibo Jin, Ruoxi Chen, Andy Zhou, Yang Zhang, Haohan Wang

ICLR 2024 Workshop on Secure and Trustworthy Large Language Models (SeT LLM@ICLR’24)

PDF / Code / Talk / DOI

CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space

Haibin Zheng, Jinyin Chen, Haibo Jin

The 38th IEEE/ACM International Conference on Automated Software Engineering (ASE’23)

PDF / Code / DOI

Excitement surfeited turns to errors: Deep learning testing framework based on excitable neurons

Haibo Jin, Ruoxi Chen, Haibin Zheng, Jinyin Chen, Yao Cheng, Yue Yu, Tieming Chen, Xianglong Liu

Information Sciences, 2023, 637: 118936

PDF / Code / DOI

ROBY: Evaluating the adversarial robustness of a deep model by its decision boundaries

Haibo Jin, Jinyin Chen, Haibin Zheng, Zhen Wang, Jun Xiao, Shanqing Yu, Zhaoyan Ming

Information Sciences, 2022, 587: 97-122

PDF / Code / DOI

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence

Ruoxi Chen, Haibo Jin, Haibin Zheng, Jinyin Chen, Zhenguang Liu

IEEE Transactions on Dependable and Secure Computing, 2024

PDF / Code

AdvCheck: Characterizing adversarial examples via local gradient checking

Ruoxi Chen, Haibo Jin, Jinyin Chen, Haibin Zheng, Shilian Zheng, Xiaoniu Yang, Xing Yang

Computers & Security, 2024, 136: 103540

PDF / Code / DOI