← authors · overview

• Prompt Injection attack against LLM-integrated Applications
  2023 · 79 citations
• Privacy-preserving Machine Learning through Data Obfuscation
  2018 · 66 citations
• DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
  2020 · 25 citations
• MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
  2023 · 17 citations
• Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques
  2020 · 14 citations
• Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey
  2021 · 9 citations
• Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
  2023 · 7 citations
• Multi-target Backdoor Attacks for Code Pre-trained Models
  2023 · 5 citations
• Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning
  2020 · 4 citations