← authors · overview

• Systematic Evaluation of Privacy Risks of Machine Learning Models
  2020 · 84 citations
• AIQL: Enabling Efficient Attack Investigation from System Monitoring Data
  2018 · 40 citations
• Inaudible Voice Commands
  2017 · 37 citations
• Neurotoxin: Durable Backdoors in Federated Learning
  2022 · 33 citations
• Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
  2021 · 22 citations
• Visual Adversarial Examples Jailbreak Aligned Large Language Models
  2023 · 13 citations
• Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
  2020 · 11 citations
• FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
  2020 · 5 citations
• BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
  2023 · 4 citations
• Teach LLMs to Phish: Stealing Private Information from Language Models
  2024 · 3 citations
• Enhancing Robustness of Machine Learning Systems via Data Transformations
  2017 · 2 citations
• A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
  2021 · 1 citations
• A Query System for Efficiently Investigating Complex Attack Behaviors for Enterprise Security
  2018