DeepAI AI Chat
Log In Sign Up

Adversarial Purification through Representation Disentanglement

by   Tao Bai, et al.

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and convenient to use because of their task independence and good generalizability. Current defense methods, especially purification, tend to remove “noise" by learning and recovering the natural images. However, different from random noise, the adversarial patterns are much easier to be overfitted during model training due to their strong correlation to the images. In this work, we propose a novel adversarial purification scheme by presenting disentanglement of natural images and adversarial perturbations as a preprocessing defense. With extensive experiments, our defense is shown to be generalizable and make significant protection against unseen strong adversarial attacks. It reduces the success rates of state-of-the-art ensemble attacks from 61.7% to 14.9% on average, superior to a number of existing methods. Notably, our defense restores the perturbed images perfectly and does not hurt the clean accuracy of backbone models, which is highly desirable in practice.


page 3

page 4

page 6

page 7


Perceptual Adversarial Robustness: Defense Against Unseen Threat Models

We present adversarial attacks and defenses for the perceptual adversari...

Defense Against Adversarial Attacks with Saak Transform

Deep neural networks (DNNs) are known to be vulnerable to adversarial pe...

Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser

Neural networks are vulnerable to adversarial examples. This phenomenon ...

Threat Model-Agnostic Adversarial Defense using Diffusion Models

Deep Neural Networks (DNNs) are highly sensitive to imperceptible malici...

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks

A powerful category of data poisoning attacks modify a subset of trainin...

Open-set Adversarial Defense with Clean-Adversarial Mutual Learning

Open-set recognition and adversarial defense study two key aspects of de...

Invertible Image Dataset Protection

Deep learning has achieved enormous success in various industrial applic...