DeepAI AI Chat
Log In Sign Up

Adversarial Robustness Against Image Color Transformation within Parametric Filter Space

by   Zhengyu Zhao, et al.

We propose Adversarial Color Enhancement (ACE), a novel approach to generating non-suspicious adversarial images by optimizing a color transformation within a parametric filter space. The filter we use approximates human-understandable color curve adjustment, constraining ACE with a single, continuous function. This property gives rise to a principled adversarial action space explicitly controlled by filter parameters. Existing color transformation attacks are not guided by a parametric space, and, consequently, additional pixel-related constraints such as regularization and sampling are necessary. These constraints make methodical analysis difficult. In this paper, we carry out a systematic robustness analysis of ACE from both the attack and defense perspectives by varying the bound of the color filter parameters. We investigate a general formulation of ACE and also a variant targeting particularly appealing color styles, as achieved with popular image filters. From the attack perspective, we provide extensive experiments on the vulnerability of image classifiers, but also explore the vulnerability of segmentation and aesthetic quality assessment algorithms, in both the white-box and black-box scenarios. From the defense perspective, more experiments provide insight into the stability of ACE against input transformation-based defenses and show the potential of adversarial training for improving model robustness against ACE.


page 6

page 13

page 14

page 15

page 16

page 17

page 19

page 20


AdvFoolGen: Creating Persistent Troubles for Deep Classifiers

Researches have shown that deep neural networks are vulnerable to malici...

Using an ensemble color space model to tackle adversarial examples

Minute pixel changes in an image drastically change the prediction that ...

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

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

Robust Person Re-identification with Multi-Modal Joint Defence

The Person Re-identification (ReID) system based on metric learning has ...

A Differentiable Color Filter for Generating Unrestricted Adversarial Images

We propose Adversarial Color Filtering (AdvCF), an approach that uses a ...

Neural Color Operators for Sequential Image Retouching

We propose a novel image retouching method by modeling the retouching pr...