Binghui Wang
Duke University
H-index: 26
North America-United States
Top articles of Binghui Wang
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Securing GNNs: Explanation-Based Identification of Backdoored Training Graphs | arXiv preprint arXiv:2403.18136 | Jane Downer Ren Wang Binghui Wang | 2024/3/26 |
Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks | Caridad Arroyo Arevalo Sayedeh Leila Noorbakhsh Yun Dong Yuan Hong Binghui Wang | 2024/2 | |
Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks | Sayedeh Leila Noorbakhsh Binghui Zhang Yuan Hong Binghui Wang | 2024/8 | |
Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function | Binghui Wang Minhua Lin Tianxiang Zhou Pan Zhou Ang Li | 2024/3/4 | |
PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models | arXiv preprint arXiv:2402.07867 | Wei Zou Runpeng Geng Binghui Wang Jinyuan Jia | 2024/2/12 |
DeepTheft: Stealing DNN Model Architectures through Power Side Channel | arXiv preprint arXiv:2309.11894 | Yansong Gao Huming Qiu Zhi Zhang Binghui Wang Hua Ma | 2023/9/21 |
Theoretically Understanding Data Reconstruction Leakage in Federated Learning | Zifan Wang Binghui Zhang Meng Pang Yuan Hong Binghui Wang | 2023/10/13 | |
IDGI: A framework to eliminate explanation noise from integrated gradients | Ruo Yang Binghui Wang Mustafa Bilgic | 2023 | |
Turning strengths into weaknesses: A certified robustness inspired attack framework against graph neural networks | Binghui Wang Meng Pang Yun Dong | 2023 | |
GraphGuard: Provably Robust Graph Classification against Adversarial Attacks | Han Yang Binghui Wang Jinyuan Jia | 2024/2 | |
Interpreting disparate privacy-utility tradeoff in adversarial learning via attribute correlation | Likun Zhang Yahong Chen Ang Li Binghui Wang Yiran Chen | 2023 | |
Text-crs: A generalized certified robustness framework against textual adversarial attacks | arXiv preprint arXiv:2307.16630 | Xinyu Zhang Hanbin Hong Yuan Hong Peng Huang Binghui Wang | 2023/7/31 |
A Certified Radius-Guided Attack Framework to Image Segmentation Models | Wenjie Qu Youqi Li Binghui Wang | 2023/7/3 | |
DisP+ V: A unified framework for disentangling prototype and variation from single sample per person | IEEE Transactions on Neural Networks and Learning Systems | Meng Pang Binghui Wang Mang Ye Yiu-ming Cheung Yiran Chen | 2021/8/17 |
A unified framework for bidirectional prototype learning from contaminated faces across heterogeneous domains | IEEE Transactions on Information Forensics and Security | Meng Pang Binghui Wang Siyu Huang Yiu-Ming Cheung Bihan Wen | 2022/4/1 |
Graphfl: A federated learning framework for semi-supervised node classification on graphs | Binghui Wang Ang Li Meng Pang Hai Li Yiran Chen | 2022/11/28 | |
Bandits for structure perturbation-based black-box attacks to graph neural networks with theoretical guarantees | Binghui Wang Youqi Li Pan Zhou | 2022 | |
BPFL: Towards Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning | Chenfei Nie Binghui Wang Yuede Ji Qiang Li | 2022/9/29 | |
Almost tight l0-norm certified robustness of top-k predictions against adversarial perturbations | Jinyuan Jia Binghui Wang Xiaoyu Cao Hongbin Liu Neil Zhenqiang Gong | 2022 | |
Variance of the gradient also matters: Privacy leakage from gradients | Yijue Wang Jieren Deng Dan Guo Chenghong Wang Xianrui Meng | 2022/7/18 |