Improved robustness to adversarial examples using Lipschitz regularization of the loss

10/01/2018
by   Chris Finlay, et al.
0

Adversarial training is an effective method for improving robustness to adversarial attacks. We show that adversarial training using the Fast Signed Gradient Method can be interpreted as a form of regularization. We implemented a more effective form of adversarial training, which in turn can be interpreted as regularization of the loss in the 2-norm, ∇_x ℓ(x)_2. We obtained further improvements to adversarial robustness, as well as provable robustness guarantees, by augmenting adversarial training with Lipschitz regularization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/25/2019

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?

Adversarial training is one of the strongest defenses against adversaria...
research
06/04/2019

Adversarial Training Generalizes Data-dependent Spectral Norm Regularization

We establish a theoretical link between adversarial training and operato...
research
03/02/2021

Smoothness Analysis of Loss Functions of Adversarial Training

Deep neural networks are vulnerable to adversarial attacks. Recent studi...
research
03/27/2019

Bridging Adversarial Robustness and Gradient Interpretability

Adversarial training is a training scheme designed to counter adversaria...
research
03/04/2021

Gradient-Guided Dynamic Efficient Adversarial Training

Adversarial training is arguably an effective but time-consuming way to ...
research
05/27/2019

Scaleable input gradient regularization for adversarial robustness

Input gradient regularization is not thought to be an effective means fo...
research
01/26/2016

Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization

Many previous proposals for adversarial training of deep neural nets hav...

Please sign up or login with your details

Forgot password? Click here to reset