Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification

by   Samuel Henrique Silva, et al.

Deep Learning models are highly susceptible to adversarial manipulations that can lead to catastrophic consequences. One of the most effective methods to defend against such disturbances is adversarial training but at the cost of generalization of unseen attacks and transferability across models. In this paper, we propose a robust defense against adversarial attacks, which is model agnostic and generalizable to unseen adversaries. Initially, with a baseline model, we extract the latent representations for each class and adaptively cluster the latent representations that share a semantic similarity. We obtain the distributions for the clustered latent representations and from their originating images, we learn semantic reconstruction dictionaries (SRD). We adversarially train a new model constraining the latent space representation to minimize the distance between the adversarial latent representation and the true cluster distribution. To purify the image, we decompose the input into low and high-frequency components. The high-frequency component is reconstructed based on the most adequate SRD from the clean dataset. In order to evaluate the most adequate SRD, we rely on the distance between robust latent representations and semantic cluster distributions. The output is a purified image with no perturbation. Image purification on CIFAR-10 and ImageNet-10 using our proposed method improved the accuracy by more than 10 state-of-the-art results.


page 1

page 3

page 6

page 7

page 10


Optimal Transport as a Defense Against Adversarial Attacks

Deep learning classifiers are now known to have flaws in the representat...

Adversarial Defense by Suppressing High-frequency Components

Recent works show that deep neural networks trained on image classificat...

Defense Against Adversarial Attacks with Saak Transform

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

WaveTransform: Crafting Adversarial Examples via Input Decomposition

Frequency spectrum has played a significant role in learning unique and ...

Reliably fast adversarial training via latent adversarial perturbation

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

Defending Adversarial Examples via DNN Bottleneck Reinforcement

This paper presents a DNN bottleneck reinforcement scheme to alleviate t...

ExpertNet: A Symbiosis of Classification and Clustering

A widely used paradigm to improve the generalization performance of high...

Please sign up or login with your details

Forgot password? Click here to reset