About Me
Hello, I am Tinghao Xie 谢廷浩, a final year ECE PhD candidate at Princeton, advised by Prof. Prateek Mittal, also a student researcher at TikTok. Previously, I was a research intern at Meta (GenAI). I earned my Bachelor degree in Computer Science at Zhejiang University.
Research Interests
- I analyze and break safety / alignment / watermark mechanisms in AI systems – particularly those built upon LLMs, VLMs, and T2I models.
- breaking security of text-to-image systems from end to end
- benchmarking safety refusal & safety durability of LLMs
- revealing how fine-tuning LLMs can compromise safety
- … (copyright, hallucinations, AIGC watermarks)
- I also aim to build secure AI systems, as well as safer & more trustworthy foundation models.
- mid-training VLMs to enhance visual knowledge
- fine-tuning VLMs for more robust safety detection
- securing AI systems against data poisoning and backdoor attacks
- …
Publications/Manuscripts
📖 Red-teaming NSFW Image Classifiers as Text-to-Image Safeguards
Tinghao Xie, Yueqi Xie, Alireza Zareian, Shuming Hu, Felix Juefei-Xu, Xiaowen Lin, Ankit Jain, Prateek Mittal, Li Chen
ACL 2026 Findings
📖 SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
Tinghao Xie*, Xiangyu Qi*, Yi Zeng*, Yangsibo Huang*, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
ICLR 2025
📖 On Evaluating the Durability of Safeguards for Open-Weight LLMs
Xiangyu Qi*, Boyi Wei*, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson
ICLR 2025
📖 Fantastic Copyrighted Beasts and How (Not) to Generate Them
Luxi He*, Yangsibo Huang*, Weijia Shi*, Tinghao Xie, Haotian Liu, Yue Wang, Luke Zettlemoyer, Chiyuan Zhang, Danqi Chen, Peter Henderson
ICLR 2025
📖 AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal
Preprint (Under Review)
📖 Assessing the brittleness of safety alignment via pruning and low-rank modifications
Boyi Wei*, Kaixuan Huang*, Yangsibo Huang*, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
ICML 2024
📖 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Xiangyu Qi*, Yi Zeng*, Tinghao Xie*, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal$^†$, Peter Henderson$^†$
ICLR 2024 (oral)
📰 This work was exclusively reported by New York Times, and covered by many other social medias!
📖 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal
ICLR 2024
📖 Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal
USENIX Security 2023
📖 Revisiting the Assumption of Latent Separability for Backdoor Defenses
Xiangyu Qi*, Tinghao Xie*, Yiming Li, Saeed Mahloujifar, Prateek Mittal
ICLR 2023
📖 Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks
Xiangyu Qi*, Tinghao Xie*, Ruizhe Pan, Jifeng Zhu, Yong Yang, Kai Bu
CVPR 2022 (oral)