← authors · overview

• Provable Defense Against Privacy Leakage In Federated Learning From Representation Perspective
  2020 · 156 citations
• FL-WBC: Enhancing Robustness Against Model Poisoning Attacks In Federated Learning From A Client Perspective
  2021 · 15 citations
• DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones
  2019 · 8 citations
• Privacy-Preserving Multiparty Learning For Logistic Regression
  2018 · 2 citations
• On Provable Backdoor Defense in Collaborative Learning
  2021 · 1 citations
• TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
  2024 · 1 citations
• Commercial LLM Agents Are Already Vulnerable To Simple Yet Dangerous Attacks
  2025
• Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
  2025
• Policycleanse: Backdoor Detection And Mitigation In Reinforcement Learning
  2022
• Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
  2020
• PredCoin: Defense against Query-based Hard-label Attack
  2021