← authors · overview

• Stealing Hyperparameters in Machine Learning
  2018 · 453 citations
• Attacking Graph-based Classification via Manipulating the Graph Structure
  2019 · 141 citations
• On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
  2020 · 59 citations
• Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
  2020 · 30 citations
• Backdoor Attacks to Graph Neural Networks
  2020 · 12 citations
• Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
  2020 · 5 citations
• DeepTheft: Stealing DNN Model Architectures through Power Side Channel
  2023 · 2 citations
• Graph Neural Network Explanations are Fragile
  2024 · 1 citations
• AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
  2025
• Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
  2025
• Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
  2020
• Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes
  2020
• Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks
  2023