Augmented Lagrangian Adversarial Attacks

Understand

Adversarial attack algorithms are dominated by penalty methods, which are slow in practice, or more efficient distance-customized methods, which are heavily tailored to the properties of the distance considered.

• We propose a white-box attack algorithm to generate minimally perturbed adversarial examples based on Augmented Lagrangian principles.
• We bring several algorithmic modifications, which have a crucial effect on performance.
• Our attack enjoys the generality of penalty methods and the computational efficiency of distance-customized algorithms, and can be readily used for a wide set of distances.