Hi! 🥰 I’m Sen Nie (聂森), a first-year Master’s student at the Visual Information Processing and Learning (VIPL) group, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). I also conduct research at the State Key Laboratory of AI Safety, under the supervision of Profs. Jie Zhang, Shiguang Shan (IEEE Fellow), and Xilin Chen (IEEE Fellow).
My research is currently focused on the frontier of AI Safety. I’m passionate about building robust and trustworthy AI systems and am always open to collaboration or a good academic chat!
🔥 News
- Feb 2026 🎉 Paper V-Attack is accepted by CVPR 2026! Thanks to all co-authors!
- Jan 2026 🥇 Our team AIST_ICT achieved 1st place in the Anti-BAD: An Anti-Backdoor Challenge for Post-Trained Large Language Models (IEEE SaTML 2026)! Congratulations to all team members!
📝 Publications
🔬 Exploring AI Safety in (Large) Vision-Language Models
Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
Sen Nie, Jie Zhang, Zhuo Wang, Shiguang Shan, Xilin Chen
arXiv preprint arXiv:2601.19210, 2026 (under review...)
CSR provides efficient, state-of-the-art adversarial robustness for VLMs by rectifying spectral inconsistencies during test time.
Sen Nie, Jie Zhang, Zhuo Wang, Shiguang Shan, Xilin Chen
arXiv preprint arXiv:2601.19210, 2026 (under review...)
CSR provides efficient, state-of-the-art adversarial robustness for VLMs by rectifying spectral inconsistencies during test time.
V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
Sen Nie, Jie Zhang, Jianxin Yan, Shiguang Shan, Xilin Chen
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
A novel adversarial attack method that targets the value features in transformer-based vision-language models to achieve precise local semantic manipulation, outperforming SOTA by 36% in success rate.
Sen Nie, Jie Zhang, Jianxin Yan, Shiguang Shan, Xilin Chen
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
A novel adversarial attack method that targets the value features in transformer-based vision-language models to achieve precise local semantic manipulation, outperforming SOTA by 36% in success rate.
📚 Others
Diverse Generation while Maintaining Semantic Coordination: A Diffusion-based Data Augmentation Method for Object Detection
Sen Nie, Zhuo Wang, Xinxin Wang, Kun He
27th International Conference on Pattern Recognition (ICPR), 2024
A novel data augmentation method using pre-trained diffusion models, featuring a Category Affinity Matrix for diversity enhancement and Surrounding Region Alignment for semantic preservation.
Sen Nie, Zhuo Wang, Xinxin Wang, Kun He
27th International Conference on Pattern Recognition (ICPR), 2024
A novel data augmentation method using pre-trained diffusion models, featuring a Category Affinity Matrix for diversity enhancement and Surrounding Region Alignment for semantic preservation.
Automatic Pricing and Replenishment Decisions for Vegetable Products Based on Price Elasticity (in Chinese)
Sen Nie, Xuanyin Pan, Haodong Qu
Mathematical Modeling and Its Applications, 2024
National First Prize (Top 0.5%) in CUMCM; Selected as a National Demonstration Paper (Top 3/All).
Sen Nie, Xuanyin Pan, Haodong Qu
Mathematical Modeling and Its Applications, 2024
National First Prize (Top 0.5%) in CUMCM; Selected as a National Demonstration Paper (Top 3/All).
🎖 Awards
- National First Prize, China Undergraduate Mathematical Contest in Modeling (CUMCM) (Top 0.5%)
- First Prize (2nd Place), Chinese Collegiate Computing Competition (Central South Region)
- First Prize, Huazhong Cup Mathematical Modeling Contest (HCMCM) (Top 0.4%)
- Scholarships: Lei Jun Computer Research Scholarship (Top 1%), NSFOCUS (LvMeng) Scholarship (Top 1%), First-Class Scholarship of Wuhan University (Top 5%)
🎖 Honors
University-Wide Recognition:
- Awarded the university’s highest graduation distinction (Outstanding Graduate)
- Recognized for exemplary research (Outstanding Undergraduate Thesis)
- Honored as a Merit Student for overall excellence (2022-2024)
Leadership & Service:
- Led class to be selected as a University-Level “Top 10 Model Class” (collective honor)
- Recognized as an Outstanding Student Leader for exceptional class management
- Awarded Outstanding Youth Volunteer for dedicated service
- Honored as an Outstanding Leader in Social Practice for spearheading field visits to major tech firms (Huawei, ByteDance, Tencent, Sangfor), resulting in exemplary extracurricular impact
📖 Education
- Sep. 2025 – Present, M.S. Candidate, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing
- Sep. 2021 – Jul. 2025, B.Eng. in Cyberspace Security, Wuhan University, Wuhan