Yulin Jin

PhD student, EEE, Hong Kong Polytechnic University

Joined

June 2022

Names

Yulin Jin (Preferred)

Jin Yulin

Emails

****@163.com (Confirmed)

Personal Links

Career & Education History

PhD student

EEE, Hong Kong Polytechnic University (connect.polyu.hk)

2024 – 2027

MS student

Cyber Security, Xidian University (stu.edu)

2021 – 2024

Advisors, Relations & Conflicts

Coauthor

Xiaoyu Zhang

2021 – 2024

Expertise

Adversarial Samples

2021 – 2024

Backdoor Attack

2021 – 2024

Information Theory

2021 – 2024

Publications

Decision Potential Surface: A Theoretical and Practical Approximation of LLM's Decision Boundary
Zi Liang, Zhiyao Wu, HaoYang Shang, Yulin Jin, Qingqing Ye, Huadi Zheng, Peizhao Hu, Haibo Hu
- Submitted to ICLR 2026
- Readers: Everyone
Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions
Haoyu Tong, Xiaoyu Zhang, Yulin Jin, Jian Lou, Kai Wu, Xiaofeng Chen
- Crossref
- Readers: Everyone
Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions
Haoyu Tong, Xiaoyu Zhang, Jin Yulin, Jian Lou, Kai Wu, Xiaofeng Chen
- MM2024 Poster
- Readers: Everyone
ACQ: Few-shot Backdoor Defense via Activation Clipping and Quantizing
Yulin Jin, Xiaoyu Zhang, Jian Lou, Xiaofeng Chen
- Crossref
- Readers: Everyone
Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective
Yulin Jin, Xiaoyu Zhang, Jian Lou, Xu Ma, Zilong Wang, Xiaofeng Chen
- ICCV 2023
- Readers: Everyone
Patch-Based Backdoors Detection and Mitigation with Feature Masking
Tao Wang, Xiaoyu Zhang, Yulin Jin, Chenyang Chen, Fei Zhu
- SocialSec 2022
- Readers: Everyone
Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression
Xiaoyu Zhang, Yulin Jin, Tao Wang, Jian Lou, Xiaofeng Chen
- 2022 (modified: 16 Apr 2023)
- ACM Multimedia 2022
- Readers: Everyone

Yulin Jin

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Decision Potential Surface: A Theoretical and Practical Approximation of LLM's Decision Boundary

Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions

Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions

ACQ: Few-shot Backdoor Defense via Activation Clipping and Quantizing

Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective

Patch-Based Backdoors Detection and Mitigation with Feature Masking

Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression

Co-Authors