← authors · overview

• Robust Anomaly Detection And Backdoor Attack Detection Via Differential Privacy
  2019 · 69 citations
• Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
  2022 · 7 citations
• Improving Robustness to Model Inversion Attacks via Mutual Information Regularization
  2020 · 6 citations
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
  2024 · 2 citations
• Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
  2026
• Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
  2025
• How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
  2022
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
  2024