Generating Adversarial Images in Quantized Domains
- 24 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 373-385
Abstract
Many adversarial attacks produce floating-point tensors which are no longer adversarial when converted to raster or JPEG images due to rounding. This paper proposes a method dedicated to quantize adversarial perturbations. This “smart” quantization is conveniently implemented as versatile post-processing. It can be used on top of any white-box attack targeting any model. Its principle is tantamount to a constrained optimization problem aiming to minimize the quantization error while keeping the image adversarial after quantization. A Lagrangian formulation is proposed and an appropriate search of the Lagrangian multiplier enables to increase the success rate. We also add a control mechanism of the $\ell _\infty $ -distortion. Our method operates in both spatial and JPEG domains with little complexity. This study shows that forging adversarial images is not a hard constraint: our quantization does not introduce any extra distortion. Moreover, adversarial images quantized as JPEG also challenge defenses relying on the robustness of neural networks against JPEG compression.Keywords
Funding Information
- Direction Générale de l’Armement, French, under the Ministry for the Armed Forces
- French National Research Agency under the ALASKA Project (ANR-18-ASTR-0009)
- DEtection de FALSifications dans des images et vidéos (DEFALS) Program (ANR-16-DEFA-0003)
- French Agence Innovation pour la Défense under the chaire Security of Artificial Intelligence for Defense Applications (ANR-20-CHIA-0011-01)
This publication has 15 references indexed in Scilit:
- What if Adversarial Samples were Digital Images?2020
- Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples2019
- High-Quality Color Image Compression by Quantization Crossing Color SpacesIEEE Transactions on Circuits and Systems for Video Technology, 2018
- 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 High Efficiency Image File Format Standard [Standards in a Nutshell]IEEE Signal Processing Magazine, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- CREW: Compression with Reversible Embedded Wavelets2002
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992