← authors · overview

• A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples
  2016
• DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
  2017
• Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
  2018
• Learning and Certification under Instance-targeted Poisoning
  2021
• Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
  2022