Evaluating a Simple Retraining Strategy as a Defense Against Adversarial Attacks

07/20/2020
by   Nupur Thakur, et al.
0

Though deep neural networks (DNNs) have shown superiority over other techniques in major fields like computer vision, natural language processing, robotics, recently, it has been proven that they are vulnerable to adversarial attacks. The addition of a simple, small and almost invisible perturbation to the original input image can be used to fool DNNs into making wrong decisions. With more attack algorithms being designed, a need for defending the neural networks from such attacks arises. Retraining the network with adversarial images is one of the simplest techniques. In this paper, we evaluate the effectiveness of such a retraining strategy in defending against adversarial attacks. We also show how simple algorithms like KNN can be used to determine the labels of the adversarial images needed for retraining. We present the results on two standard datasets namely, CIFAR-10 and TinyImageNet.

READ FULL TEXT

page 7

page 8

page 9

page 10

page 11

page 12

page 14

page 15

research
09/05/2020

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

Deep neural networks (DNNs) are now commonly used in many domains. Howev...
research
09/23/2020

Detection of Iterative Adversarial Attacks via Counter Attack

Deep neural networks (DNNs) have proven to be powerful tools for process...
research
06/02/2020

Exploring the role of Input and Output Layers of a Deep Neural Network in Adversarial Defense

Deep neural networks are learning models having achieved state of the ar...
research
05/16/2019

Fooling Computer Vision into Inferring the Wrong Body Mass Index

Recently it's been shown that neural networks can use images of human fa...
research
01/21/2020

Generate High-Resolution Adversarial Samples by Identifying Effective Features

As the prevalence of deep learning in computer vision, adversarial sampl...
research
05/04/2022

CE-based white-box adversarial attacks will not work using super-fitting

Deep neural networks are widely used in various fields because of their ...
research
12/20/2022

Multi-head Uncertainty Inference for Adversarial Attack Detection

Deep neural networks (DNNs) are sensitive and susceptible to tiny pertur...

Please sign up or login with your details

Forgot password? Click here to reset