← authors · overview

• Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
  2024 · 5 citations
• Black-box Detection of Backdoor Attacks with Limited Information and Data
  2021 · 3 citations
• Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
  2023 · 2 citations
• BadDLM: Backdooring Diffusion Language Models with Diverse Targets
  2026
• MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
  2026
• Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
  2025
• Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
  2025
• Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
  2025
• Your Diffusion Model Is Secretly A Certifiably Robust Classifier
  2024
• Automated Decision-based Adversarial Attacks
  2021
• Accumulative Poisoning Attacks On Real-time Data
  2021
• Kallima: A Clean-label Framework for Textual Backdoor Attacks
  2022