DeepAI AI Chat
Log In Sign Up

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

by   Hanbin Hong, et al.
Rochester Institute of Technology
Illinois Institute of Technology

Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which contains critical information for generating malicious perturbations. In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks. By using both gradient maps and adversarial images as inputs, we propose a Two-stream Restoration Network (TRN) to restore the adversarial images. To optimally restore the perturbed images with two streams of inputs, a Gradient Map Estimation Mechanism is proposed to estimate the gradients of adversarial images, and a Fusion Block is designed in TRN to explore and fuse the information in two streams. Once trained, our TRN can defend against a wide range of attack methods without significantly degrading the performance of benign inputs. Also, our method is generalizable, scalable, and hard to bypass. Experimental results on CIFAR10, SVHN, and Fashion MNIST demonstrate that our method outperforms state-of-the-art defense methods.


page 1

page 3

page 4

page 8


Robust SleepNets

State-of-the-art convolutional neural networks excel in machine learning...

Sampled Nonlocal Gradients for Stronger Adversarial Attacks

The vulnerability of deep neural networks to small and even imperceptibl...

Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation

Deep Neural Network based classifiers are known to be vulnerable to pert...

Local Gradients Smoothing: Defense against localized adversarial attacks

Deep neural networks (DNNs) have shown vulnerability to adversarial atta...

Visualizing Representations of Adversarially Perturbed Inputs

It has been shown that deep learning models are vulnerable to adversaria...

Improving Resistance to Adversarial Deformations by Regularizing Gradients

Improving the resistance of deep neural networks against adversarial att...