DeepAI AI Chat
Log In Sign Up

Encryption Inspired Adversarial Defense for Visual Classification

by   MaungMaung AprilPyone, et al.

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.


page 1

page 2

page 3

page 4


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

In this paper, we propose a novel defensive transformation that enables ...

Adversarial Defense via Image Denoising with Chaotic Encryption

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

Reliably fast adversarial training via latent adversarial perturbation

While multi-step adversarial training is widely popular as an effective ...

RAILS: A Robust Adversarial Immune-inspired Learning System

Adversarial attacks against deep neural networks are continuously evolvi...

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Trojan attacks on deep neural networks are both dangerous and surreptiti...

Symmetry Subgroup Defense Against Adversarial Attacks

Adversarial attacks and defenses disregard the lack of invariance of con...

Visual Prompting for Adversarial Robustness

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