2025

• Recipient-Aware Photo Automatic Deletion Control Policy Recommendation Scheme in Online Social Networks
  Haiyang Luo, Zhe Sun, Yunqing Sun, Ang Li, Binghui Wang, Jin Cao, and Ben Niu
  IEEE Transactions on Dependable and Secure Computing (TDSC), 2025
  

• PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models
  Wei Zou, Runpeng Geng, Binghui Wang, Jinyuan Jia
  Usenix Security Symposium (SEC), 2025
  

2024

• FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
  Yuxin Yang, Qiang Li, Yuan Hong, Binghui Wang
  Neural Information Processing Systems (NeurIPS), 2024
  

• Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
  Yuxin Yang, Qiang Li, Jinyuan Jia, Yuan Hong, Binghui Wang
  ACM Conference on Computer and Communications Security (CCS), 2024
  Distinguished Paper Award

• Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
  Hanbin Hong, Xinyu Zhang, Binghui Wang, Zhongjie Ba, Yuan Hong
  ACM Conference on Computer and Communications Security (CCS), 2024
  

• Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
  Sayedeh Leila Noorbakhsh*, Binghui Zhang*, Yuan Hong, Binghui Wang
  Usenix Security Symposium (SEC), 2024

• Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
  Xinyu Zhang, Hanbin Hong, Yuan Hong, Peng Huang, Binghui Wang, Zhongjie Ba, Kui Ren
  IEEE Symposium on Security and Privacy (SP), 2024

• DeepTheft: Stealing DNN Model Architectures through Power Side Channel
  Yansong Gao, Huming Qiu, Zhi Zhang, Binghui Wang, Hua Ma
  IEEE Symposium on Security and Privacy (SP), 2024

• Graph Neural Network Causal Explanation via Neural Causal Models
  Arman Behnam, Binghui Wang
  European Conference on Computer Vision (ECCV), 2024
  

• Graph Neural Network Explanations are Fragile
  Jiate Li, Meng Pang", Yun Dong, Jinyuan Jia, Binghui Wang" ("Corresponding authors)
  International Conference on Machine Learning (ICML), 2024

• Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
  Zaishuo Xia*, Han Yang*, Jinyuan Jia", Binghui Wang" (*Co-first authors, "Corresponding authors)
  International Conference on Learning Representations (ICLR), 2024
  Oral presentation

• 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
  AAAI Conference on Artificial Intelligence (AAAI), 2024

• Heterogeneous Prototype Learning From Contaminated Faces Across Domains via Disentangling Latent Factors
  Meng Pang, Binghui Wang, Mang Ye, Yiu-Ming Cheung, Yintao Zhou, Wei Huang, Bihan Wen
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024

• Breaking State-of-the-Art Poisoning Defenses to Federated Learning: An Optimization-Based Attack Framework
  Yuxin Yang, Qiang Li, Chenfei Nie, Yuan Hong, Binghui Wang
  ACM International Conference on Information and Knowledge Management (CIKM), 2024
  

• Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach
  Ruo Yang, Binghui Wang and Mustafa Bilgic
  ACM International Conference on Information and Knowledge Management (CIKM), 2024
  

• 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, Meng Pang, Hai Li, Yiran Chen (*Equal contribution)
  ACM International Conference Web Search and Data Mining (WSDM), 2024

• Reconstructing Prototype From Contaminated Face With Variations Across Heterogeneous Domains
  Meng Pang, Binghui Wang, Nanrun Zhou, Yintao Zhou, Wei Huang
  IEEE Conference on Multimedia Expo (ICME), 2024
  Oral presentation

• Early Diagnosing Parkinson's Disease Via A Deep Learning Model Based On Augmented Facial Expression Data
  Yintao Zhou, Meng Pang, Wei Huang, Binghui Wang
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

2023

• A Certified Radius-Guided Attack Framework to Image Segmentation Models
  Wenjie Qu*, Youqi Li*, Binghui Wang (*Equal contribution)
  IEEE European Symposium on Security and Privacy (EuroSP), 2023

• Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks
  Binghui Wang, Meng Pang, Yun Dong
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

• IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients
  Ruo Yang, Binghui Wang, Mustafa Bilgic
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

• DisP+V: A Unified Framework for Disentangling Prototype and Variation from Single Sample per Person
  Meng Pang, Binghui Wang, Mang Ye, Yiu-ming Cheung, Yiran Chen, Bihan Wen
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
  

• Interpreting Disparate Privacy-Utility Tradeoff in Adversarial Learning via Attribute Correlation
  Likun Zhang, Yahong Chen, Ang Li, Binghui Wang, Yiran Chen, Fenghua Li, Jin Cao, Ben Niu
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023

2022

• NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
  Nuo Xu, Binghui Wang, Ran Ran, Wujie Wen, Parv Venkitasubramaniam
  Annual Computer Security Applications Conference (ACSAC), 2022

• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
  Binghui Wang, Ang Li, Meng Pang, Hai Li, Yiran Chen
  IEEE International Conference on Data Mining (ICDM), 2022, regular paper

• Cross-domain Prototype Learning from Contaminated Faces via Disentangling Latent Factors
  Meng Pang, Binghui Wang, Shengbo Chen, Yiu-ming Cheung, Rong Zou, Wei Huang
  ACM International Conference on Information and Knowledge Management (CIKM), 2022
  

• UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
  Hanbin Hong, Binghui Wang, Yuan Hong
  European Conference on Computer Vision (ECCV), 2022
  

• Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees [Code]
  Binghui Wang, Youqi Li, Pan Zhou
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  Oral presentation

• GraphTrack: A Graph-based Cross-Device Tracking Framework
  Binghui Wang, Tianchen Zhou, Song Li, Yinzhi Cao, Neil Zhenqiang Gong
  ACM ASIA Conference on Computer and Communications Security (AsiaCCS), 2022
  

• Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations
  Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong
  International Conference on Learning Representations (ICLR), 2022
  

• A Unified Framework for Bidirectional Prototype Learning from Contaminated Faces across Heterogeneous Domains
  Meng Pang, Binghui Wang, Siyu Huang, Yiu-ming Cheung, Bihan Wen
  

• IEEE Transactions on Information Forensics and Security (TIFS), 2022

2021

• Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs
  Houxiang Fan, Binghui Wang, Pan Zhou, Ang Li, Zichuan Xu, Cai Fu, Hai Li, Yiran Chen
  IEEE International Conferences on High Performance Computing and Communications (HPCC), 2021
  

• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks for Graph Classification [Code]
  Jiaming Mu, Binghui Wang* , Qi Li, Kun Sun, Mingwei Xu, Zhuotao Liu (*Advisor)
  ACM Conference on Computer and Communications Security (CCS), 2021
  

• On Detecting Growing-Up Behaviors of Malicious Accounts in Privacy-Centric Mobile Social Networks
  Zijie Yang, Binghui Wang, Haoran Li, Dong Yuan, Zhuotao Liu, Neil Gong, Chang Liu, Qi Li, Xiao Liang, Shaofeng Hu
  In Annual Computer Security Applications Conference (ACSAC), 2021
  

• LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets
  Ang Li, Jingwei Sun, Binghui Wang, Lin Duan, Sicheng Li, Yiran Chen, Hai Li
  In ACM/IEEE Symposium on Edge Computing (SEC), 2021
  

• Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting
  Qiming Wu, Zhikang Zou, Pan Zhou, Xiaoqing Ye, Binghui Wang, Ang Li
  ACM Multimedia (MM), 2021
  

• Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
  Binghui Wang, Jiayi Guo, Ang Li, Yiran Chen and Hai Li
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Research track, 2021
  Acceptance rate: 238/1541=15.4%
  

• Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation [Code]
  Binghui Wang, Jinyuan Jia, Xiaoyu Cao, and Neil Zhenqiang Gong
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Research track, 2021
  Acceptance rate: 238/1541=15.4%
  

• Unveiling Fake Accounts at the Time of Registration: An Unsupervised Approach
  Binghui Wang*, Xiao Liang*, Zheng Yang*, Shaofeng Hu, Zijie Yang, Dong Yuan, Neil Zhenqiang Gong, Qi Li, and Fang He (*Equal contribution)
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied data science track, 2021
  Acceptance rate: 138/705=19.6%
  

• Backdoor Attacks to Graph Neural Networks
  Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong
  ACM Symposium on Access Control Models and Technologies (SACMAT), 2021
  

• Disentangling Prototype and Variation for Single Sample Face Recognition
  Meng Pang, Binghui Wang, Mang Ye, Yiran Chen, Bihan Wen
  IEEE International International Conference on Multimedia and Expo (ICME), 2021
  Acceptance rate: 15%
  Oral presentation

• Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
  Jingwei Sun, Ang Li, Binghui Wang, Huanrui Yang, Hai Li, Yiran Chen
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  Acceptance rate: 1663/7015 = 23.7%
  

• Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks
  Binghui Wang, Jinyuan Jia, Neil Zhenqiang Gong
  AAAI Conference on Artificial Intelligence (AAAI), 2021
  Acceptance rate: 1692/7911= 21.4%
  

• Robust and Verifiable Information Embedding At- tacks to Deep Neural Networks via Error-Correcting Codes
  Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong
  ACM Asia Conference on Computer and Communications Security (AisaCCS), 2021
  Acceptance rate: 29/157 = 18.5%
  

• VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person
  Meng Pang, Binghui Wang, Yiu-ming Cheung, Yiran Chen, Bihan Wen
  IEEE Transactions on Information Forensics and Security (TIFS), 2021

• Joint Traffic Control and Multi-Channel Reassignment for Core Backbone Network in SDN-IoT: A Multi-Agent Deep Reinforcement Learning Approach
  Tong Wu, Pan Zhou, Binghui Wang, Ang Li, Xueming Tang, Zichuan Xu, Kai Chen, Xiaofeng Ding
  IEEE Transactions on Network Science and Engineering (TNSE), 2021

2020

• Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
  Nathan Inkawhich, Kevin J Liang, Binghui Wang, Matthew Inkawhich, Lawrence Carin, Yiran Chen
  Neural Information Processing Systems (NeurIPS), 2020
  Acceptance rate: 1900/9454 = 20.1%

• On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
  Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong
  CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision, 2020
  DeepMind Best Extended Abstract

• Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing
  Binghui Wang*, Jinyuan Jia*, Xiaoyu Cao, and Neil Zhenqiang Gong (*Equal contribution)
  The Web Conference (TheWebConf), 2020

• Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
  Jinyuan Jia, Xiaoyu Cao, Binghui Wang, and Neil Zhenqiang Gong
  International Conference on Learning Representations (ICLR), 2020
  Acceptance rate: 687/2594= 26.5%
  

• Synergistic Generic Learning for Face Recognition from a Contaminated Single Sample per Person
  Meng Pang, Yiu-ming Cheung, Binghui Wang, and Jian Lou
  IEEE Transactions on Information Forensics and Security (TIFS), 2020

• Robust Heterogeneous Discriminative Analysis for Face Recognition with Single Sample per Person
  Meng Pang, Yiu-ming Cheung, Binghui Wang, and Risheng Liu
  Pattern Recognition (PR), 2020

2019 and Before

• Attacking Graph-based Classification via Manipulating the Graph Structure [Code]
  Binghui Wang, and Neil Zhenqiang Gong
  ACM Conference on Computer and Communications Security (CCS), 2019
  Acceptance rate: 149/933= 16.0%
  

• Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation
  Binghui Wang, Jinyuan Jia, and Neil Zhenqiang Gong
  ISOC Network and Distributed System Security Symposium (NDSS), 2019
  Acceptance rate: 89/521= 17.1%
  Distinguished Paper Award Honorable Mention
  

• Structure-based Sybil Detection in Social Networks via Local Rule-based Propagation [Code]
  Binghui Wang, Jinyuan Jia, Le Zhang, and Neil Zhenqiang Gong
  IEEE Transactions on Network Science and Engineering (TNSE), 2019 (Fast tracked from our INFOCOM’17 paper)

• SybilBlind: Sybil Detection in Social Web Services without Requiring Manual Labels
  Binghui Wang*, Le Zhang*, and Neil Zhenqiang Gong (*Equal contribution)
  International Symposium on Research in Attacks, Intrusions and Defenses (RAID), 2018
  Acceptance rate: 33/145=22.8%

• Stealing Hyperparameters in Machine Learning
  Binghui Wang and Neil Zhenqiang Gong
  IEEE Symposium on Security and Privacy (IEEE S & P), 2018
  Acceptance rate: 63/549=11.5%

• SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection
  Peng Gao, Binghui Wang, Neil Zhenqiang Gong, Sanjeev Kulkarni, Kurt Thomas, and Prateek Mittal
  IEEE Conference on Communications and Network Security (CNS), 2018
  Acceptance rate: 51/181=28.2%

• GANG: Detecting Fraudulent Users in Online Social Networks via Guilt-by-Association on Directed Graphs [Code]
  Binghui Wang, Neil Zhenqiang Gong, and Hao Fu
  IEEE International Conference on Data Mining (ICDM), 2017, regular paper
  Acceptance rate: 72/778=9.25%

• Random Walk based Fake Account Detection in Online Social Networks
  Jinyuan Jia, Binghui Wang, and Neil Zhenqiang Gong
  IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2017
  Acceptance rate: 49/220=22.3%

• AttriInfer: Inferring User Attributes in Online Social Networks Using Markov Random Fields
  Jinyuan Jia, Binghui Wang, Le Zhang, and Neil Zhenqiang Gong
  26th International World Wide Web conference (WWW), 2017
  Acceptance rate: 164/966=17.0%

• SybilSCAR: Sybil Detection in Online Social Networks via Local Rule based Propagation [Code]
  Binghui Wang, Le Zhang, and Neil Zhenqiang Gong
  IEEE International Conference on Computer Communications (INFOCOM), 2017
  Acceptance rate: 292/1395=20.9% (Top-10 out of 292 accepted papers)

• Robust Heterogeneous Discriminative Analysis for Single Sample Per Person Face Recognition
  Meng Pang, Yiu-ming Cheung, Binghui Wang, and Risheng Liu
  International Conference on Information and Knowledge Management (CIKM), 2016
  Acceptance rate: 30%

• Discriminant Manifold Learning via Sparse Coding for Image Analysis
  Meng Pang, Binghui Wang, Chuang Lin, and Xin Fan
  LNCS International Conference on MultiMedia Modeling (MMM), 2016

• Matrix Factorization with Column L0 Constraint for Robust Subspace Analysis
  Binghui Wang, Risheng Liu, Chuang Lin, and Xin Fan
  IEEE International Conference on Data Mining Workshop, 2015

• Graph Regularized Nonnegative Matrix Factorization with Sparse Coding
  Binghui Wang, Meng Pang, Chuang Lin, Xin Fan
  IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP), 2013.

• Robust extraction of basis functions for simultaneous and proportional myoelectric control via sparse non-negative matrix factorization
  Chuang Lin, Binghui Wang, Ning Jiang, and Dario Farina
  Journal of Neural Engineering (JNE), 2018

• Discriminant Manifold Learning via Sparse Coding with Application to Image Classification and Clustering
  Binghui Wang*, Meng Pang*, Yiu-ming Cheung, and Chuang Lin
  IEEE Access, 2017

• Discriminative Manifold Learning based Online Detection of Movement-Related Cortical Potentials
  Chuang Lin, Binghui Wang, Ning Jiang, Ren Xu, and Dario Farina
  IEEE Transactions on Neural Systems & Rehabilitation Engineering (TNSRE), 2016

• Orthogonal Enhanced Linear Discriminant Analysis for Face Recognition
  Chuang Lin, Binghui Wang, Xin Fan, Yanchun Ma, and Huiyun Liu
  IET Biometrics, 2016

• Hierarchical Bayes based Adaptive Sparsity in Gaussian Mixture Model
  Binghui Wang, Chuang Lin, Xin Fan, Ning Jiang, and Dario Farina
  Pattern Recognition Letters (PRL), 2014

• Neighborhood Sensitive Preserving Embedding for Pattern Classification
  Binghui Wang, Chuang Lin, Xuefeng Zhao, Zhemeng Lu
  IET Image Processing, 2014

• Optimizing Kernel PCA Using Sparse Representation-Based Classifier for MSTAR SAR Image Recognition
  Chuang Lin, Binghui Wang, Xuefeng Zhao, Meng Pang
  Mathematical Problems in Engineering, 2013