Improved Adversarial Robustness via Logit Regularization Methods
arXiv:1906.03749
Abstract
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input, known as adversarial examples, which represent a security threat for learned vision models in the wild -- a threat which should be responsibly defended against in safety-critical applications of computer vision. In this paper, we advocate for and experimentally investigate the use of a family of logit regularization techniques as an adversarial defense, which can be used in conjunction with other methods for creating adversarial robustness at little to no marginal cost. We also demonstrate that much of the effectiveness of one recent adversarial defense mechanism can in fact be attributed to logit regularization, and show how to improve its defense against both white-box and black-box attacks, in the process creating a stronger black-box attack against PGD-based models. We validate our methods on three datasets and include results on both gradient-free attacks and strong gradient-based iterative attacks with as many as 1,000 steps.
References in corpus (9)
- Distilling the Knowledge in a Neural Network
- AutoAugment: Learning Augmentation Policies from Data
- Adversarially Robust Generalization Requires More Data
- Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Data Augmentation by Pairing Samples for Images Classification
- Motivating the Rules of the Game for Adversarial Example Research
- Evaluating and Understanding the Robustness of Adversarial Logit Pairing