Follow
Xiao Zhang
Xiao Zhang
CISPA Helmholtz Center for Information Security
Verified email at cispa.de - Homepage
Title
Cited by
Cited by
Year
Learning one-hidden-layer relu networks via gradient descent
X Zhang, Y Yu, L Wang, Q Gu
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2019
1612019
A unified computational and statistical framework for nonconvex low-rank matrix estimation
L Wang, X Zhang, Q Gu
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2017
922017
A unified framework for nonconvex low-rank plus sparse matrix recovery
X Zhang, LW Wang, Q Gu
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2018
48*2018
A primal-dual analysis of global optimality in nonconvex low-rank matrix recovery
X Zhang, L Wang, Y Yu, Q Gu
International Conference on Machine Learning (ICML), 2018, 2018
472018
Autodefense: Multi-agent llm defense against jailbreak attacks
Y Zeng, Y Wu, X Zhang, H Wang, Q Wu
arXiv preprint arXiv:2403.04783, 2024
432024
Fast and sample efficient inductive matrix completion via multi-phase procrustes flow
X Zhang, SS Du, Q Gu
International Conference on Machine Learning (ICML), 2018, 2018
312018
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
S Zhu, X Zhang, D Evans
International Conference on Machine Learning (ICML), 2020, 2020
282020
A unified variance reduction-based framework for nonconvex low-rank matrix recovery
L Wang, X Zhang, Q Gu
International Conference on Machine Learning (ICML), 2017, 2017
27*2017
Cost-Sensitive Robustness against Adversarial Examples
X Zhang, D Evans
International Conference on Learning Representations (ICLR), 2019, 2019
262019
Robust wirtinger flow for phase retrieval with arbitrary corruption
J Chen, L Wang, X Zhang, Q Gu
arXiv preprint arXiv:1704.06256, 2017
262017
Empirically measuring concentration: Fundamental limits on intrinsic robustness
S Mahloujifar, X Zhang, M Mahmoody, D Evans
NeurIPS 2019, 2019
242019
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
X Zhang, J Chen, Q Gu, D Evans
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2020
162020
Understanding Intrinsic Robustness using Label Uncertainty
X Zhang, D Evans
International Conference on Learning Representations (ICLR), 2022, 2022
8*2022
Improved Estimation of Concentration under Lp-norm Distance Metrics using Half Spaces
JB Prescott, X Zhang, D Evans
International Conference on Learning Representations (ICLR) 2021, 2021
72021
A unified framework for low-rank plus sparse matrix recovery
X Zhang, L Wang, Q Gu
arXiv preprint arXiv:1702.06525, 2017
62017
Stealthy Targeted Backdoor Attacks against Image Captioning
W Fan, H Li, W Jiang, M Hao, S Yu, X Zhang
IEEE Transactions on Information Forensics and Security, 2024
42024
Do Parameters Reveal More than Loss for Membership Inference?
A Suri, X Zhang, D Evans
arXiv preprint arXiv:2406.11544, 2024
32024
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?
F Suya, X Zhang, Y Tian, D Evans
Advances in neural information processing systems (NeurIPS 2023) 36, 2023
3*2023
Transferable availability poisoning attacks
Y Liu, M Backes, X Zhang
arXiv preprint arXiv:2310.05141, 2023
32023
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
AR Basani, X Zhang
arXiv preprint arXiv:2411.14133, 2024
12024
The system can't perform the operation now. Try again later.
Articles 1–20