I am Associate Professor and Empire Innovation Scholar in the Department of Computer Science at Stony Brook University. I conduct research at the interface of machine learning, privacy and security, and aim to develop safe and trustworthy artificial intelligence (AI) technologies. Specifically, my recent work focuses on improving AI methods and systems along three major thrusts:
Before joining Stony Brook, I was Associate Professor in the College of IST at Penn State. I finished my Ph.D. at Georgia Tech and my undergrad study at Zhejiang University.
I lead the Algorithmic Learning, Privacy, and Security (ALPS) lab, where I am privileged to work alongside a team of exceptional talents, both in the past and present:
Current Members – Ren Pang, Changjiang Li, Jiacheng Liang, Tanqiu Jiang, Ziyi Yin (co-supervised with Fenglong Ma), Zian Wang, Lauren Hong
Alumni – Tianyu Du (» Assistant Professor@Zhejiang University), Zhaohan Xi (» Assistant Professor@Binghamton University), Xinyang Zhang (» Senior Engineer@Google), Tinghao Xie (» Ph.D.@Princeton), Zheng Zhang (» Ph.D.@Northwestern), Ningfei Wang (» Ph.D.@UC Irvine), Yujie Ji (» Engineer@Amazon), Sam Nguyen (» Engineer@Google), Yifan Huang (» Engineer@Bloomberg)
Join Us! – We are ALWAYS looking for motivated and bright (under)grad students and postdocs. If you know how to build/hack AI systems, we should talk! Please email me your resume and set up a time to discuss your potential fit to our team.
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Changjiang Li, Ren Pang, Bochuan Cao, Zhaohan Xi, Jinghui Chen, Shouling Ji, Ting Wang
USENIX Security Symposium (USENIX’24)
Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
Lujia Shen, Yuwen Pu, Shouling Ji, Changjiang Li, Xuhong Zhang, Chunpeng Ge, Ting Wang
Network and Distributed System Security Symposium (NDSS’24)
Model Extraction Attacks Revisited
Jiacheng Liang, Ren Pang, Changjiang Li, Ting Wang
ACM ASIA Conference on Computer and Communications Security (ASIACCS’24)
Generative AI in the Wild: Prospects, Challenges, and Strategies
Yuan Sun, Eunchae Jang, Fenglong Ma, Ting Wang
ACM CHI Conference on Human Factors in Computing Systems (CHI’24)
ReMasker: Imputing Tabular Data with Masked Autoencoding [code]
Tianyu Du, Luca Melis, Ting Wang
International Conference on Learning Representations (ICLR’24)
Backdoor Contrastive Learning via Bi-level Trigger Optimization
Weiyu Sun, Xinyu Zhang, Hao Lu, Ying-Cong Chen, Ting Wang, Jinghui Chen, Lu Lin
International Conference on Learning Representations (ICLR’24)
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
Tianrong Zhang, Zhaohan Xi, Prasenjit Mitra, Ting Wang, Jinghui Chen
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’24)
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
Ziyi Yin, Muchao Ye, Tianrong Zhang, Jiaqi Wang, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
AAAI Conference on Artificial Intelligence (AAAI’24)
Inspecting Prediction Confidence for Detecting Black-box Backdoor Attacks
Tong Wang, Yuan Yao, Feng Xu, Miao Xu, Shengwei An, Ting Wang
AAAI Conference on Artificial Intelligence (AAAI’24)
Powered by Jekyll and Minimal Light theme.