Publications

Advik Raj Basani, Xiao Zhang (2024). GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs. ArXiv.

PDF Cite Code ArXiv

Anshuman Suri, Xiao Zhang, David Evans (2024). Do Parameters Reveal More than Loss for Membership Inference?. TMLR 2024.

PDF Cite Code ArXiv OpenReview

Jia Fu, Xiao Zhang, Sepideh Pashami, Fatemeh Rahimian, Anders Holst (2024). DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination. WACV 2025.

Minxing Zhang, Michael Backes, Xiao Zhang (2024). Generating Less Certain Adversarial Examples Improves Robust Generalization. TMLR 2024.

PDF Cite Code ArXiv OpenReview

Santanu Rathod, Pietro Liò, Xiao Zhang (2024). Predicting Time-varying Flux and Balance in Metabolic Systems using Structured Neural ODE Processes. ArXiv.

Minxing Zhang, Michael Backes, Xiao Zhang (2024). Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks. ArXiv.

Somrita Ghosh, Yuelin Xu, Xiao Zhang (2024). Improving the Efficiency of Self-Supervised Adversarial Training through Latent Clustering-based Selection. ICML 2024 NextGenAISafety Workshop.

PDF Cite OpenReview

Yuelin Xu, Xiao Zhang (2024). Understanding Adversarially Robust Generalization via Weight-Curvature Index. ICML 2024 HiLD Workshop.

PDF Cite ArXiv OpenReview

Wenshu Fan, Hongwei Li, Wenbo Jiang, Meng Hao, Shui Yu, Xiao Zhang (2024). Stealthy Targeted Backdoor Attacks against Image Captioning. TIFS 2024.

PDF Cite Link ArXiv

Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, Qingyun Wu (2024). AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. ArXiv.

PDF Cite Code ArXiv

Fnu Suya, Xiao Zhang, Yuan Tian, David Evans (2023). What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?. NeurIPS 2023.

Yuan Xin, Michael Backes, Xiao Zhang (2023). Provably Robust Cost-Sensitive Learning via Randomized Smoothing. ArXiv.

PDF Cite Code ArXiv

Yiyong Liu, Michael Backes, Xiao Zhang (2023). Transferable Availability Poisoning Attacks. ArXiv.

PDF Cite Code ArXiv

Xiao Zhang, David Evans (2022). Understanding Intrinsic Robustness using Label Uncertainty. ICLR 2022.

PDF Cite Code ArXiv OpenReview

Xiao Zhang, David Evans (2021). Incorporating Label Uncertainty in Intrinsic Robustness Measures. ICLR 2021 aisecure workshop.

PDF Code Poster Link

Jack Prescott, Xiao Zhang, David Evans (2021). Improved Estimation of Concentration Under Lp-Norm Distance Metric Using Half Spaces. ICLR 2021.

PDF Cite Code ArXiv OpenReview Post

Xiao Zhang, Jinghui Chen, Quanquan Gu, David Evans (2020). Understanding the intrinsic robustness of image distributions using conditional generative models. AISTATS 2020.

PDF Cite Code Slides ArXiv Link

Sicheng Zhu, Xiao Zhang, David Evans (2020). Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization. ICML 2020.

PDF Cite Code ArXiv Link Post

Saeed Mahloujifar, Xiao Zhang, Mohammad Mahmoody, David Evans (2019). Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness. NeurIPS 2019 (Spotlight).

PDF Cite Code Poster ArXiv Post

Xiao Zhang, David Evans (2019). Cost-Sensitive Robustness against Adversarial Examples. ICLR 2019.

PDF Cite Code Poster ArXiv OpenReview Post

Xiao Zhang, Yaodong Yu, Lingxiao Wang, Quanquan Gu (2019). Learning One-hidden-layer ReLU Networks via Gradient Descent. AISTATS 2019.

PDF Cite Poster ArXiv Link

Xiao Zhang, Simon Du, Quanquan Gu (2018). Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow. ICML 2018.

PDF Cite Code Poster ArXiv Link

Xiao Zhang, Lingxiao Wang, Yaodong Yu, Quanquan Gu (2018). A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery. ICML 2018.

Xiao Zhang, Lingxiao Wang, Quanquan Gu (2018). A Unified Framework for Nonconvex Low-rank plus Sparse Matrix Recovery. AISTATS 2018.

PDF Cite Code Poster ArXiv Link

Lingxiao Wang, Xiao Zhang, Quanquan Gu (2017). A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery. ICML 2017.

PDF Cite Code Poster ArXiv Link

Jinghui Chen, Lingxiao Wang, Xiao Zhang, Quanquan Gu (2017). Robust Wirtinger Flow for Phase Retrieval with Arbitrary Corruption. ArXiv.

Lingxiao Wang, Xiao Zhang, Quanquan Gu (2017). A Unified Computational and Statistical Framework for Nonconvex Low-rank Matrix Estimation. AISTATS 2017.

PDF Cite Poster ArXiv Link