余益

2014.08-2019.06  清华大学  自动化专业  学士

2019.09-2020.12  美国加州大学圣地亚哥分校  电子与计算机工程专业  硕士

2021.01-2025.08  新加坡南洋理工大学  电子与电气工程专业  博士

2025.09-2026.03  新加坡南洋理工大学  研究员

2026.05-至今  吉林大学   “唐敖庆学者”领军教授A岗 博导

从事人工智能领域研究，致力于提升人工智能系统全生命周期的安全性、可靠性与隐私保护能力。主要研究方向包括：

1. 人工智能安全：关注大模型和智能体中的安全、评测、对齐和可信推理等问题

2. 空间智能与具身智能：重点关注AI在物理世界（具身智能、世界模型等）的可靠性与安全性

3.机器学习：关注类脑计算，组合优化，强化学习和优化剪枝等方向

4. AI for Science：关注人工智能与化学、生物等学科的交叉应用

担任ICLR、ICML、NeurIPS、 IJCNN、VCIP等会议领域主席（Area Chair）；担任IEEE TPAMI客座编委；担任 IEEE TPAMI、TIFS、TIP、TCSVT、TMM、TNNLS、CVIU、Nature npj AI、TMLR 等期刊审稿人，以及CVPR、ICCV、NeurIPS、ICLR、ICML、ACM MM、AAAI、KDD等国际会议审稿人

数字图像处理 本科

统计机器学习基础 本科

人工智能安全导论 本科

欢迎有志青年报考我的研究生，需要具备扎实的数学基础、程序设计能力（包括但不限于MATLAB、C/C++、Python等）与英文读写能力。本人每年招收博士研究生2名，硕士研究生3-4名。

1.国家自然科学基金青年科学基金项目（C类）：“开放环境下数据训练权保护的安全机理与统一方法研究”，项目负责人，资助经费30万元，2027-2029年。

2.国家自然科学基金优秀青年科学基金项目（海外）：“视觉模型安全机制与可信防御理论方法”，项目负责人，资助经费200万元，2026—2028年。（另有校级别配套经费200万元）

余益，国家级青年人才，吉林大学“唐敖庆学者”领军教授A岗，博士生导师。目前从事人工智能安全、空间智能、机器学习等方面的研究工作，论文均发表在中国计算机学会（CCF）所认定的A类顶级会议和顶级期刊上。

主要学术论文：

1. Yi Yu, Yufei Wang, Wenhan Yang, Lanqing Guo, Shijian Lu, Ling-Yu Duan, Yap-Peng Tan and Alex C. Kot, "Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (CCF A, JCR Q1, 中科院一区TOP, IF: 20.4)

2. Yi Yu, Qixin Zhang, Shuhan Ye, Xun Lin, Qianshan Wei, Kun Wang, Wenhan Yang, Dacheng Tao and Xudong Jiang, "Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks," International Conference on Learning Representations (ICLR), 2026. (CCF A)

3. Hui Lu, Yi Yu*, Yiming Yang, ChenYu Yi, Qixin Zhang, Bingquan Shen, Alex C. Kot and Xudong Jiang, "When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF A, Highlight, 2.8% acceptance rate) (*通讯作者)

4. Jiaming He, Guanyu Hou, Hongwei Li, Zhicong Huang, Kangjie Chen, Yi Yu*, Wenbo Jiang, Guowen Xu and Tianwei Zhang, "TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF A, Oral, 0.7% acceptance rate) (*共同通讯作者)

5. Yi Yu, Song Xia, Siyuan Yang, Chenqi Kong, Wenhan Yang, Shijian Lu, Yap-Peng Tan and Alex C. Kot, "MTL-UE: Learning to Learn Nothing for Multi-Task Learning," International Conference on Machine Learning (ICML), 2025. (CCF A)

6. Yi Yu, Song Xia, Xun Lin, Chenqi Kong, Wenhan Yang, Shijian Lu, Yap-Peng Tan and Alex C. Kot, "Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation," IEEE Transactions on Information Forensics and Security (TIFS), 2025. (CCF A, JCR Q1, 中科院一区TOP, IF: 8.7)

7. Yi Yu, Song Xia, Xun Lin, Wenhan Yang, Shijian Lu, Yap-Peng Tan and Alex C. Kot, "Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger," AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A)

8. Yi Yu, Yufei Wang, Song Xia, Wenhan Yang, Shijian Lu, Yap-Peng Tan and Alex C. Kot, "Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders," International Conference on Machine Learning (ICML), 2024. (CCF A)

9. Yi Yu, Yufei Wang, Wenhan Yang, Shijian Lu, Yap-Peng Tan and Alex C. Kot, "Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (CCF A)

10. Yi Yu, Wenhan Yang, Yap-Peng Tan and Alex C. Kot, "Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (CCF A)

11. Hui Lu, Yi Yu*, Song Xia, Yiming Yang, Deepu Rajan, Boon Poh Ng, Alex C. Kot and Xudong Jiang, "From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge," AAAI Conference on Artificial Intelligence (AAAI), 2026. (CCF A, Oral, 4% acceptance rate) (*通讯作者)

12. Qixin Zhang, Qirun Zeng, Hui Lu, Pingchuan Ma, Jinhang Zuo, Renqiang Luo, Yi Yu* and Dacheng Tao, "One Rounding Fits All: Memory-Efficient Approximation Algorithms for Partition-Constrained Influence Maximization," SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. (CCF A) (*共同通讯作者)

13. Hui Lu, Yi Yu*, Shijian Lu, Deepu Rajan, Boon Poh Ng, Alex C. Kot and Xudong Jiang, "MambaTAD: Leveraging State-Space Models for Long-Range Temporal Action Detection," IEEE Transactions on Multimedia (TMM), 2026. (CCF A, JCR Q1, 中科院一区TOP, IF: 9.9) (*通讯作者)

14. Guoqing Ma, Xun Lin, Hui Ma, Ajian Liu, Yizhong Liu, Wenzhong Tang, Shan Yu, Chenqi Kong and Yi Yu*, "StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting," Machine Intelligence Research (MIR), 2026. (JCR Q1, 中科院二区TOP, IF: 10.0) (*通讯作者)

15. Qiangqiang Wu#, Yi Yu#, Chenqi Kong, Ziquan Liu, Jia Wan, Haoliang Li, Alex C. Kot and Antoni B. Chan, "Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking," IEEE/CVF International Conference on Computer Vision (ICCV), 2025. (CCF A) (#共同第一作者)

16. Xun Lin#, Yi Yu#, Zitong Yu, Ruohan Meng, Jiale Zhou, Ajian Liu, Yizhong Liu, Shuai Wang, Wenzhong Tang, Zhen Lei and Alex C. Kot, "HideMIA: Hidden Wavelet Mining for Privacy-Enhancing Medical Image Analysis," ACM International Conference on Multimedia (ACM MM), 2024. (CCF A) (#共同第一作者)