← authors · overview

• Defending Pre-trained Language Models As Few-shot Learners Against Backdoor Attacks
  2023 · 12 citations
• ER-MIA: Black-box Adversarial Memory Injection Attacks On Long-term Memory-augmented Large Language Models
  2026
• The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
  2026
• Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
  2025
• Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
  2025
• On The Security Risks Of Automl
  2021