← authors · overview

• Can You Really Backdoor Federated Learning?
  2019 · 368 citations
• Privacy-preserving Instructions For Aligning Large Language Models
  2024 · 41 citations
• Can Llms Get Help From Other Llms Without Revealing Private Information?
  2024 · 11 citations
• Back To The Drawing Board: A Critical Evaluation Of Poisoning Attacks On Production Federated Learning
  2021 · 9 citations
• Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
  2026
• Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
  2026
• Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
  2026
• A Technical Policy Blueprint for Trustworthy Decentralized AI
  2025
• Toward provably private analytics and insights into GenAI use
  2025
• Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
  2025
• Advances and Open Problems in Federated Learning
  2019
• AirGapAgent: Protecting Privacy-Conscious Conversational Agents
  2024