Binghui Wang

Affiliations

Iowa State University

papers

237

total citations

papers (14)

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

NEURIPS 2020arXiv

citations

IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients

CVPR 2023arXiv

citations

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks

AAAI 2024arXiv

citations

Graph Neural Network Explanations are Fragile

ICML 2024arXiv

citations

Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks

CVPR 2023arXiv

citations

Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees

CVPR 2022arXiv

citations

Practicable Black-Box Evasion Attacks on Link Prediction in Dynamic Graphs—a Graph Sequential Embedding Method

AAAI 2025arXiv

citations

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

CVPR 2025arXiv

citations

Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective

CVPR 2021

citations

Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis

AAAI 2025

citations

Measure-Theoretic Anti-Causal Representation Learning

NEURIPS 2025arXiv

citations

Binghui Wang

Affiliations

papers (14)

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks

Graph Neural Network Explanations are Fragile

Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks

Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

Graph Neural Network Causal Explanation via Neural Causal Models

Learning Robust and Privacy-Preserving Representations via Information Theory

Practicable Black-Box Evasion Attacks on Link Prediction in Dynamic Graphs—a Graph Sequential Embedding Method

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective

Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis

Measure-Theoretic Anti-Causal Representation Learning

papers (14)

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks

Graph Neural Network Explanations are Fragile

Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks

Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

Graph Neural Network Causal Explanation via Neural Causal Models

Learning Robust and Privacy-Preserving Representations via Information Theory

Practicable Black-Box Evasion Attacks on Link Prediction in Dynamic Graphs—a Graph Sequential Embedding Method

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective

Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis

Measure-Theoretic Anti-Causal Representation Learning