← authors · overview

• Extracting Training Data from Large Language Models
  2020 · 275 citations
• Defensive Distillation is Not Robust to Adversarial Examples
  2016 · 240 citations
• Label-Only Membership Inference Attacks
  2020 · 98 citations
• Membership Inference Attacks From First Principles
  2021 · 30 citations
• Handcrafted Backdoors in Deep Neural Networks
  2021 · 20 citations
• Poisoning Web-Scale Training Datasets is Practical
  2023 · 15 citations
• Is Private Learning Possible with Instance Encoding?
  2020 · 11 citations
• Backdoor Attacks for In-Context Learning with Language Models
  2023 · 10 citations
• A critique of the DeepSec Platform for Security Analysis of Deep Learning Models
  2019 · 7 citations
• A Partial Break of the Honeypots Defense to Catch Adversarial Attacks
  2020 · 7 citations
• Stealing Part of a Production Language Model
  2024 · 7 citations
• Students Parrot Their Teachers: Membership Inference on Model Distillation
  2023 · 6 citations
• Privacy Side Channels in Machine Learning Systems
  2023 · 6 citations
• Stateful Detection of Black-Box Adversarial Attacks
  2019 · 5 citations
• Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
  2022 · 4 citations