I am Haibo Jin, a PhD student majoring in Information Sciences, at the University of Illinois Urbana-Champaign, under the supervision of Prof. Haohan Wang.

Before that, I obtained my B.E. degree in Communication Engineering at the College of Information Engineering, Zhejiang University of Technology.

My research interest includes trustworthy machine learning and the robustness of deep learning systems. I am now working on attacks and defense on computer vision, diffusion models, and multi-modal models. If you are seeking any form of academic cooperation, please feel free to email me.

🔥 News

• 2024.11:  🎉🎉 Welcome to visit JAM website.
• 2024.10:  🎉🎉 Submit our paper: Jailbreaking LLM-Generated Content Detectors via Psychological Effects Guided Subtle Typos to NAACL’25!
• 2024.10:  🎉🎉 Submit our paper: GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models to ICLR’25!
• 2024.10:  🎉🎉 Submit our paper: GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing to ICLR’25!
• 2024.10:  🎉🎉 Submit our paper: HessianGrad: Optimizing AI Systems with Hessian-Aware Textual Gradients to ICLR’25!
• 2024.09:  🎉🎉 Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters is accepted by NeurIPS’24!
• 2024.08:  🎉🎉 Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence is accepted by IEEE Transactions on Dependable and Secure Computing (TDSC)!
• 2024.07:  🎉🎉 CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing is accepted by ECCV’24!
• 2024.07:  🎉🎉 EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models is accepted by ECCV’24!
• 2024.06:  🎉🎉 Welcome to visit JailbreakZoo website.
• 2024.05:  🎉🎉 Welcome to my new homepage!
• 2024.04:  🎉🎉 Receive a TA/RA offer from the School of Information Sciences, University of Illinois Urbana-Champaign!
• 2024.03:  🎉🎉 Welcome to visit JailbreakZoo, a dedicated repository focused on the jailbreaking of large models (LMs), encompassing both large language models (LLMs) and vision language models (VLMs).
• 2024.01:  🎉🎉 Start my trip at the University of Illinois Urbana-Champaign as a vising scholar!

📝 Selected Publications

NeurIPS'24

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

ECCV'24

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

ECCV'24

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

SeT LLM@ICLR'24

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

ASE'23

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

Information Sciences'23

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

Information Sciences'22

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

TDSC'24

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

Computers & Security'24

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

🎖️ Honors and Awards

• 2022.10:   National Scholarship, Postgraduate Premium Scholarship.
• 2022.04:   Zhejiang University of Technology “Top 10 Academic Stars” Scholarship.
• 2021.10:   Postgraduate Premium Scholarship.

📖 Educations

• 2024.09 - now:   PhD Candicate, Information Sciences, University of Illinois Urbana-Champaign, Illinois, US.
• 2020.09 - now:   PhD Candicate, Control Science and Engineering, Zhejiang University of Technology, Hangzhou, China.
• 2016.09 - 2020.06:   Undergraduate, Communication Engineering, Zhejiang University of Technology, Hangzhou, China.

💻 Internships

• 2023.04 - 2024.06:   Visiting scholar at DREAM Lab, University of Illinois Urbana-Champaign, US. (Supervisor: Haohan Wang)

🔖 Service

• 2025:   ICLR 2025, AISTATS 2025
• 2024:   NeurIPS 2024, ICML 2024, WWW 2024, SeT LLM @ ICLR 2024