Tinghao Xie

According to our database, Tinghao Xie authored at least 11 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

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

CoRR, 2024

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

CoRR, 2024

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

CoRR, 2024

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

Proceedings of the Forty-first International Conference on Machine Learning, 2024

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection.

Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal

Proceedings of the Twelfth International Conference on Learning Representations, 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

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Towards A Proactive ML Approach for Detecting Backdoor Poison Samples.

Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal

Proceedings of the 32nd USENIX Security Symposium, 2023

Revisiting the Assumption of Latent Separability for Backdoor Defenses.

Xiangyu Qi, Tinghao Xie, Yiming Li, Saeed Mahloujifar, Prateek Mittal

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Fight Poison with Poison: Detecting Backdoor Poison Samples via Decoupling Benign Correlations.

Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal

CoRR, 2022

Circumventing Backdoor Defenses That Are Based on Latent Separability.

Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal

CoRR, 2022

Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.

Xiangyu Qi, Tinghao Xie, Ruizhe Pan, Jifeng Zhu, Yong Yang, Kai Bu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022