ColorFool: Semantic Adversarial Colorization
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1148-1157
Abstract
Adversarial attacks that generate small Lp norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to adversarial training procedures. Instead, adversarial attacks that generate unrestricted perturbations are more robust to defenses, are generally more successful in black-box settings and are more transferable to unseen classifiers. However, unrestricted perturbations may be noticeable to humans. In this paper, we propose a content-based black-box adversarial attack that generates unrestricted perturbations by exploiting image semantics to selectively modify colors within chosen ranges that are perceived as natural by humans. We show that the proposed approach, ColorFool, outperforms in terms of success rate, robustness to defense frameworks and transferability, five state-of-the-art adversarial attacks on two different tasks, scene and object classification, when attacking three state-of-the-art deep neural networks using three standard datasets. The source code is available at https://github.com/smartcameras/ColorFool.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Places: A 10 Million Image Database for Scene RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Scene Parsing through ADE20K Dataset2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- The Limitations of Deep Learning in Adversarial Settings2016
- AVA: A large-scale database for aesthetic visual analysis2012
- ImageNet: A large-scale hierarchical image database2009
- Colorization using optimizationACM Transactions on Graphics, 2004
- Statistics of cone responses to natural images: implications for visual codingJournal of the Optical Society of America A, 1998