← authors · overview

• Understanding Membership Inferences on Well-Generalized Learning Models
  2018 · 164 citations
• Prompt Injection attack against LLM-integrated Applications
  2023 · 79 citations
• CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition
  2018 · 77 citations
• Invisible Mask: Practical Attacks on Face Recognition with Infrared
  2018 · 70 citations
• Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
  2019 · 44 citations
• Malla: Demystifying Real-world Large Language Model Integrated Malicious Services
  2024 · 9 citations
• Understanding Impacts of Task Similarity on Backdoor Attack and Detection
  2022 · 2 citations
• Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
  2025 · 1 citations
• Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
  2023 · 1 citations
• LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
  2026
• RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
  2025
• A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
  2025