← authors · overview

• Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
  2018 · 182 citations
• Are Attribute Inference Attacks Just Imputation?
  2022 · 43 citations
• Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
  2017 · 41 citations
• Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
  2019 · 34 citations
• Query-limited Black-box Attacks to Classifiers
  2017 · 14 citations
• Context-aware Monitoring in Robotic Surgery
  2019 · 14 citations
• When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
  2026
• Advances and Open Problems in Federated Learning
  2019
• Stealthy Backdoors as Compression Artifacts
  2021