← authors · overview

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
  2017 · 1032 citations
• Robust Physical-World Attacks on Deep Learning Models
  2017 · 508 citations
• Extracting Training Data from Large Language Models
  2020 · 275 citations
• Spatially Transformed Adversarial Examples
  2018 · 242 citations
• Generating Adversarial Examples with Adversarial Networks
  2018 · 240 citations
• TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
  2019 · 134 citations
• Physical Adversarial Examples for Object Detectors
  2018 · 104 citations
• Note on Attacking Object Detectors with Adversarial Stickers
  2017 · 37 citations
• ThreatKG: An AI-Powered System for Automated Open-Source Cyber Threat Intelligence Gathering and Management