Benoît Bonnet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Benoît Bonnet has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Teddy Furon
Centre Inria de lUniversit de Rennes, Rennes, France
3 shared publications - Patrick Bas
Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL, Villeneuve D'Ascq, France
2 shared publications - Patrick Bas
CRIStAL Lab CNRS Ecole Centrale de Lille 59651 Villeneuve d'Ascq Cedex France
1 shared publication
Latest Publications
- 24 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 373-385
Generating Adversarial Images in Quantized Domains
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.
- 24 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 373-385
Generating Adversarial Images in Quantized Domains
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.
- 25 February 2021
- Published by Springer Nature
- p. 453-469
Forensics Through Stega Glasses: The Case of Adversarial Images
- 25 February 2021
- Published by Springer Nature
- p. 453-469
Forensics Through Stega Glasses: The Case of Adversarial Images
- Open Access
Adversarial Images through Stega Glasses
This paper explores the connection between steganography and adversarial images. On the one hand, ste-ganalysis helps in detecting adversarial perturbations. On the other hand, steganography helps in forging adversarial perturbations that are not only invisible to the human eye but also statistically undetectable. This work explains how to use these information hiding tools for attacking or defending computer vision image classification. We play this cat and mouse game with state-of-art classifiers, steganalyzers, and steganographic embedding schemes. It turns out that steganography helps more the attacker than the defender.
Open AccessAdversarial Images through Stega Glasses
This paper explores the connection between steganography and adversarial images. On the one hand, ste-ganalysis helps in detecting adversarial perturbations. On the other hand, steganography helps in forging adversarial perturbations that are not only invisible to the human eye but also statistically undetectable. This work explains how to use these information hiding tools for attacking or defending computer vision image classification. We play this cat and mouse game with state-of-art classifiers, steganalyzers, and steganographic embedding schemes. It turns out that steganography helps more the attacker than the defender.