← authors · overview

• Extracting Training Data from Large Language Models
  2020 · 275 citations
• Physical Adversarial Examples for Object Detectors
  2018 · 104 citations
• Label-Only Membership Inference Attacks
  2020 · 98 citations
• Note on Attacking Object Detectors with Adversarial Stickers
  2017 · 37 citations
• Membership Inference Attacks From First Principles
  2021 · 30 citations
• Red-Teaming the Stable Diffusion Safety Filter
  2022 · 25 citations
• JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
  2024 · 15 citations
• Is Private Learning Possible with Instance Encoding?
  2020 · 11 citations
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
  2024 · 9 citations
• The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks And Prompt Injections
  2025 · 3 citations
• Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
  2024 · 3 citations
• Evading Black-box Classifiers Without Breaking Eggs
  2023
• Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
  2024
• Blind Baselines Beat Membership Inference Attacks for Foundation Models
  2024