Defense Against the Dark Arts: An overview of adversarial example security research and future research directions

Abstract

This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.

Cited by in corpus (13)

• When Machine Learning Meets Privacy: A Survey and Outlook
• Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
• RANDOM MASK: Towards Robust Convolutional Neural Networks
• Requisite Variety in Ethical Utility Functions for AI Value Alignment
• Adversarial Token Attacks on Vision Transformers
• Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness
• The Efficacy of SHIELD under Different Threat Models
• Towards Making Deep Learning-based Vulnerability Detectors Robust
• Collaborative Sampling in Generative Adversarial Networks
• Cross-Layer Strategic Ensemble Defense Against Adversarial Examples
• Robust Deep Learning Ensemble against Deception
• Robusta: Robust AutoML for Feature Selection via Reinforcement Learning
• Law and Adversarial Machine Learning