Tinghao Xie

Cited by

	All	Since 2019
Citations	386	386
h-index	5	5
i10-index	5	5

280

140

210

20212022202320241 16 102 265

Public access

View all

1 article

0 articles

available

not available

Based on funding mandates

Co-authors

Xiangyu QIPrinceton UniversityVerified email at princeton.edu
Prateek MittalProfessor, Princeton UniversityVerified email at princeton.edu
Peter HendersonPrinceton UniversityVerified email at princeton.edu
Yi ZengPhD Candidate, Virginia TechVerified email at vt.edu
Ruoxi JiaAssistant Professor, Virginia TechVerified email at vt.edu
Saeed MahloujifarFAIR, MetaVerified email at meta.com
Pin-Yu ChenPrincipal Research Scientist, IBM Research AI; MIT-IBM Watson AI Lab; RPI-IBM AIRCVerified email at ibm.com
Yiming LiNanyang Technological UniversityVerified email at ntu.edu.sg
Yangsibo HuangGoogleVerified email at google.com
Kaixuan HuangPrinceton UniversityVerified email at princeton.edu
Mengdi WangCenter for Statistics & Machine Learning, ECE, Princeton UniversityVerified email at princeton.edu
Kai BuZhejiang UniversityVerified email at zju.edu.cn
Pan RuizheVerified email at zju.edu.cn
Mengzhou XiaPrinceton UniversityVerified email at princeton.edu
Tong WuPrinceton UniversityVerified email at princeton.edu
Jiachen T. WangPrinceton UniversityVerified email at princeton.edu
Luxi HeDepartment of Computer Science, Princeton UniversityVerified email at princeton.edu
Udari Madhushani SehwagVisiting Postdoc, Stanford University / Research Scientist, JPMorgan AI ResearchVerified email at stanford.edu
Weijia ShiUniversity of WashingtonVerified email at uw.edu
Luke ZettlemoyerUniversity of Washington; MetaVerified email at cs.washington.edu

Tinghao Xie

Princeton University

Verified email at princeton.edu - Homepage

Computer Security AI Security Adversarial ML Machine Learning


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Fine-tuning aligned language models compromises safety, even when users do not intend to! X Qi, Y Zeng, T Xie, PY Chen, R Jia, P Mittal, P Henderson ICLR 2024 (Oral), 2023	189	2023
Revisiting the assumption of latent separability for backdoor defenses X Qi, T Xie, Y Li, S Mahloujifar, P Mittal ICLR 2023, 2022	81*	2022
Towards practical deployment-stage backdoor attack on deep neural networks X Qi, T Xie, R Pan, J Zhu, Y Yang, K Bu CVPR 2022 (Oral), 13347-13357, 2022	54	2022
Towards a proactive {ML} approach for detecting backdoor poison samples X Qi, T Xie, JT Wang, T Wu, S Mahloujifar, P Mittal 32nd USENIX Security Symposium (USENIX Security 23), 1685-1702, 2023	29*	2023
Assessing the brittleness of safety alignment via pruning and low-rank modifications B Wei, K Huang, Y Huang, T Xie, X Qi, M Xia, P Mittal, M Wang, ... ICML 2024, 2024	27	2024
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection T Xie, X Qi, P He, Y Li, JT Wang, P Mittal ICLR 2024, 2023	5	2023
Fantastic Copyrighted Beasts and How (Not) to Generate Them L He, Y Huang, W Shi, T Xie, H Liu, Y Wang, L Zettlemoyer, C Zhang, ... arXiv preprint arXiv:2406.14526, 2024	1	2024
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors T Xie, X Qi, Y Zeng, Y Huang, UM Sehwag, K Huang, L He, B Wei, D Li, ... arXiv preprint arXiv:2406.14598, 2024		2024
AI Risk Management Should Incorporate Both Safety and Security X Qi, Y Huang, Y Zeng, E Debenedetti, J Geiping, L He, K Huang, ... arXiv preprint arXiv:2405.19524, 2024		2024
A Handbook for Deep Learning with their Piecemeal Intuitions from Causal Theory T Xie		2021
Ensemble of Narrow DNN Chains T Xie		2021
Texture Packing T Xie, H Lin, Z Zhao		2020

The system can't perform the operation now. Try again later.

Articles 1–12

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors