Robert Sabourin

Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses

Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems. Considering L2 norm distortions, the Carlini and Wagner attack is presen…