Publications

Malicious Forgetting: Backdoor Injection in Active Federated Unlearning and Countermeasure Design

[cite_start]

Authors: Wenwei Zhao, Yanni Peng, Xiaowen Li, Jie Xu, Yao Liu, and Zhuo Lu [cite: 65]

[cite_start]

Conference: IEEE INFOCOM, Tokyo, Japan, 2026 [cite: 66] | BibTeX

Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary Statistics

[cite_start]

Authors: Wenwei Zhao, Xiaowen Li, Shangqing Zhao, Jie Xu, Yao Liu, and Zhuo Lu [cite: 67]

[cite_start]

Conference: IEEE Conference on Computer Communications (INFOCOM), May, 2024 [cite: 67] | PDF | BibTeX


Under Review & Theses

Perception-Guided Large Perturbation Attacks against Adversarial Training of Neural Networks

[cite_start]

Authors: Xiaowen Li, Wenwei Zhao, Ren Pang, Yao Liu, and Zhuo Lu [cite: 57]

[cite_start]

Journal: Submitted to IEEE Transactions on Dependable and Secure Computing (TDSC) [cite: 58]

Adapter-Based Parameter-Efficient Adversarial Training for Enhanced Clean Accuracy

[cite_start]

Authors: Xiaowen Li, Wenwei Zhao, Yao Liu, and Zhuo Lu [cite: 59]

[cite_start]

Conference: Submitted to IEEE ICASSP 2026 [cite: 60]

Dynamic Sparse Defense Updating: Discovering Robustness-Critical Subnetworks

[cite_start]

Authors: Xiaowen Li, Wenwei Zhao, Yao Liu, and Zhuo Lu [cite: 61]

[cite_start]

Conference: Submitted to IEEE ICASSP 2026 [cite: 62]

Consistency-Preserving Logit Shaping for Robust Model Stealing Defense

[cite_start]

Authors: Xiaowen Li, Wenwei Zhao, Yao Liu, and Zhuo Lu [cite: 63]

[cite_start]

Conference: Submitted to IEEE ICASSP 2026 [cite: 64]

Randomized Algorithms for Solving Singular Value Decomposition Problems with Matlab Toolbox

[cite_start]

Author: Xiaowen Li [cite: 68]

[cite_start]

Thesis: Master's thesis, Dept. Math., University of Kansas, 2021 [cite: 68, 69]