DeepAI AI Chat
Log In Sign Up

Encryption Inspired Adversarial Defense for Visual Classification

05/16/2020
by   MaungMaung AprilPyone, et al.
0

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a new adversarial defense which is a defensive transform for both training and test images inspired by perceptual image encryption methods. The proposed method utilizes a block-wise pixel shuffling method with a secret key. The experiments are carried out on both adaptive and non-adaptive maximum-norm bounded white-box attacks while considering obfuscated gradients. The results show that the proposed defense achieves high accuracy (91.55 and (89.66 dataset. Thus, the proposed defense outperforms state-of-the-art adversarial defenses including latent adversarial training, adversarial training and thermometer encoding.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/02/2020

Block-wise Image Transformation with Secret Key for Adversarially Robust Defense

In this paper, we propose a novel defensive transformation that enables ...
03/19/2022

Adversarial Defense via Image Denoising with Chaotic Encryption

In the literature on adversarial examples, white box and black box attac...
04/04/2021

Reliably fast adversarial training via latent adversarial perturbation

While multi-step adversarial training is widely popular as an effective ...
12/18/2020

RAILS: A Robust Adversarial Immune-inspired Learning System

Adversarial attacks against deep neural networks are continuously evolvi...
02/24/2022

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Trojan attacks on deep neural networks are both dangerous and surreptiti...
10/08/2022

Symmetry Subgroup Defense Against Adversarial Attacks

Adversarial attacks and defenses disregard the lack of invariance of con...
10/12/2022

Visual Prompting for Adversarial Robustness

In this work, we leverage visual prompting (VP) to improve adversarial r...