Xin Wang

Xin Wang

Researcher · Shanghai AI Laboratory

Email Google Scholar GitHub LinkedIn

I’m currently a Researcher at Shanghai AI Laboratory, collaborating with Dr. Yan Teng and Prof. Xia Hu. Previously, I received my Ph.D. degree from FVL Lab in the College of Computer Science and Artificial Intelligence, Fudan University, supervised by Prof. Xingjun Ma and Prof. Yu-Gang Jiang.

Recently, I am broadly interested in safety and privacy aspects of machine learning, with a recent focus on large language models, vision-language-action models, and world models.

Feel free to reach me at hsinwang22 [at] gmail [dot] com, if you are interested in potential collaborations.

Publications

2026
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
Xin Wang, Yunhao Chen, Juncheng Li, Yixu Wang, Yang Yao, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang, Xia Hu
Technical Report, 2026
Paper Code Project
NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
Jiaming Zhang, Xin Wang, Xinjun Ma, Lingyu Qiu, Yu-Gang Jiang, Jitao Sang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
Paper Code
Towards Context-Invariant Safety Alignment for Large Language Models
Yixu Wang, Yang Yao, Xin Wang, Yifeng Gao, Yan Teng, Xingjun Ma, Yingchun Wang
International Conference on Machine Learning (ICML), Seoul, South Korea, 2026
Paper
FakeWorld 1.0: An Omni modal Benchmark for Fake Media and Content
Yifeng Gao, Yifan Ding, Li Wang, Feida Huang, Ye Sun, Yixu Wang, Xin Wang, Yutao Wu, Hanxun Huang, Yunhao Feng, Yingshui Tan, Xingjun Ma, Yu-Gang Jiang
International Conference on Machine Learning (ICML), Seoul, South Korea, 2026
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
Yixu Wang, Xin Wang, Yang Yao, Xinyuan Li, Yan Teng, Xingjun Ma, Yingchun Wang
Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), San Diego, USA, 2026
Paper
Probing the Safety Robustness of LLMs in Latent Space
Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang
Annual Meeting of the Association for Computational Linguistics (ACL), San Diego, USA, 2026
Paper Code
Adversarial Prompt Distillation for Vision-Language Models
Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun Ma
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2026
Paper
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia, Yixu Wang, Xin Wang, Ye Sun, Yunhan Zhao, Ming Wen, Jiayu Li, Xun Gong, Yi Liu, Yige Li, Yutao Wu, Cong Wang, Jun Sun, Yixin Cao, Zhineng Chen, Jingjing Chen, Tao Gui, Qi Zhang, Zuxuan Wu, Xipeng Qiu, Xuanjing Huang, Tiehua Zhang, Zhipeng Wei, Hanxun Huang, Sarah Erfani, James Bailey, Jianping Wang, Wei-Ying Ma, Bo Li, Xingjun Ma, Yu-Gang Jiang
arXiv, 2026
Project
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Xingjun Ma, Yixu Wang, Hengyuan Xu, Yutao Wu, Yifan Ding, Yunhan Zhao, Zilong Wang, Jiabin Hua, Ming Wen, Jianan Liu, Ranjie Duan, Yifeng Gao, Yingshui Tan, Yunhao Chen, Hui Xue, Xin Wang, Wei Cheng, Jingjing Chen, Zuxuan Wu, Bo Li, Yu-Gang Jiang
Technical Report, 2026
Paper
TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
Xin Wang, Yixu Wang, Jiaming Zhang, Ruofan Wang, Jiaqi Yu, Kai Chen, Jingjing Chen, Xingjun Ma, Yu-Gang Jiang
arXiv, 2026
Paper Code
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
Ye Sun*, Xin Wang*, Jiaming Zhang, Yifeng Gao, Yixu Wang, Qixian Zhang, Henghui Ding, Xingjun Ma, Yu-Gang Jiang
arXiv, 2026
Paper
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jiaqi Yu*, Xin Wang*, Yixu Wang, Jie Li, Yan Teng, Xingjun Ma, Yingchun Wang
arXiv, 2026
Paper
2025
TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
Xin Wang, Kai Chen, Jiaming Zhang, Jingjing Chen, Xingjun Ma
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, 2025
Paper Code
FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
Xin Wang, Jie Li, Zejia Weng, Yixu Wang, Yifeng Gao, Tianyu Pang, Chao Du, Yan Teng, Yingchun Wang, Zuxuan Wu, Xingjun Ma, Yu-Gang Jiang
arXiv, 2025
Paper Code
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law
Core Contributor, Shanghai AI Laboratory
Technical Report, 2025
Paper Code Project
SafeVid: Toward Safety-Aligned Video Large Multimodal Models
Yixu Wang, Jiaxin Song, Yifeng Gao, Xin Wang, Yang Yao, Yan Teng, Xingjun Ma, Yingchun Wang, Yu-Gang Jiang
Advances in Neural Information Processing Systems (NeurIPS), San Diego, USA, 2025
Paper
Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes? (Oral)
Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang
ACM Multimedia (MM), Dublin, Ireland, 2025
Paper
Safety at Scale: A Comprehensive Survey of Large Model Safety
Xinjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, Hanxun Huang, Yige Li, Yutao Wu, Jiaming Zhang, Xiang Zheng, Yang Bai, Zuxuan Wu, Xipeng Qiu, Jingfeng Zhang, Yiming Li, Xudong Han, Haonan Li, Jun Sun, Cong Wang, Jindong Gu, Baoyuan Wu, Siheng Chen, Tianwei Zhang, Yang Liu, Mingming Gong, Tongliang Liu, Shirui Pan, Cihang Xie, Tianyu Pang, Yinpeng Dong, Ruoxi Jia, Yang Zhang, Shiqing Ma, Xiangyu Zhang, Neil Gong, Chaowei Xiao, Sarah Erfani, Tim Baldwin, Bo Li, Masashi Sugiyama, Dacheng Tao, James Bailey, Yu-Gang Jiang
Foundations and Trends® in Privacy and Security, 2025
Paper
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen*, Xin Wang*, Juncheng Li, Yixu Wang, Jie Li, Yan Teng, Yingchun Wang, Xingjun Ma
arXiv, 2025
Paper Code
Simulated Ensemble Attack: Transferable Jailbreaks Across Fine-tuned Vision-Language Models
Ruofan Wang, Xin Wang, Yang Yao, Xuan Tong, Xingjun Ma
arXiv, 2025
Paper
A2RM: Adversarial-Augmented Reward Model
Shiyang Huang, Jie Li, Xin Wang, Xiaoya Ma, Yixu Wang, Xuefeng Xi, Yan Teng, Yingchun Wang
arXiv, 2025
LeakyCLIP: Extracting Training Data from CLIP
Yunhao Chen, Shujie Wang, Xin Wang, Xingjun Ma
arXiv, 2025
Paper
Imperceptible Jailbreaking against Large Language Models
Kuofeng Gao, Yiming Li, Chao Du, Xin Wang, Xingjun Ma, Shu-Tao Xia, Tianyu Pang
arXiv, 2025
Paper Code
Test-Time Safety Adaptation for Multimodal Large Models via Contrastive Steering
Jie Li, Shiyang Huang, Chi Xie, Xin Wang, Yixu Wang, Yan Teng, Yingchun Wang
arXiv, 2025
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang
arXiv, 2025
Paper
DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning
Yifeng Gao, Yifan Ding, Hongyu Su, Juncheng Li, Yunhan Zhao, Lin Luo, Zixing Chen, Li Wang, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang
arXiv, 2025
Paper Code
Surveying the Value Alignment Cycle in LLMs: Representation, Intervention, Evaluation, and Impact
Tianle Gu, Kaiwen Xia, Lingyu Li, Huacan Liu, Xinyuan Li, Yixu Wang, Yuxia Wang, Zongqi Wang, Kexin Huang, Xin Wang, Yujiu Yang, Yan Teng, Yingchun Wang
arXiv, 2025
2024 and Earlier
AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
Xin Wang, Kai Chen, Xinjun Ma, Zhineng Chen, Jingjing Chen, Yu-Gang Jiang
ACM Multimedia (MM), Melbourne, Australia, 2024
Paper Code
Adversarial Prompt Tuning for Vision-Language Models
Jiaming Zhang, Xinjun Ma, Xin Wang, Lingyu Qiu, Jiaqi Wang, Yu-Gang Jiang, Jitao Sang
European Conference on Computer Vision (ECCV), Milano, Italy, 2024
Paper Code
Lossless Medical Image Compression Based on Anatomical Information and Deep Neural Networks
Qiusha Min, Xin Wang, Bo Huang, Zhongwei Zhou
Biomedical Signal Processing and Control, 2022
Paper
Web-Based Technology for Remote Viewing of Radiological Images: App Validation
Qiusha Min*, Xin Wang*, Bo Huang, Liangzhou Xu
Journal of Medical Internet Research (JMIR), 2020
Paper

Honors & Awards

Professional Service