arXiv subjects

Pol Labarbarie

Publications and source records attributed to Pol Labarbarie.

3 recordsLinked to original sources

arXiv2025

Secure and reversible face anonymization with diffusion models

Face anonymization aims to protect sensitive identity information by altering faces while preserving visual realism and utility for downstream computer vision tasks. Current methods struggle to simultaneously ensure high image quality, strong security guarantees, and controlled reversibility for authorized identity recovery at a later time. To improve the image quality of generated anonymized faces, recent methods have adopted diffusion models. However, these new diffusion-based anonymization methods do not provide a mechanism to restrict de-anonymization to trusted parties, limiting their real-world applicability. In this paper, we present the first diffusion-based framework for secure, reversible face anonymization via secret-key conditioning. Our method injects the secret key directly into the diffusion process, enabling anonymization and authorized face reconstruction while preventing unauthorized de-anonymization. The use of deterministic forward and reverse diffusion steps guarantees exact identity recovery when the correct secret key is available. Experiments on CelebA-HQ and LFW demonstrate that our approach achieves better anonymization and de-anonymization capabilities than prior work. We also show that our method remains robust to incorrect or adversarial key de-anonymization. Our code will be made publicly available.

cs.CV↗

arXiv2022

Carpet-bombing patch: attacking a deep network without usual requirements

Although deep networks have shown vulnerability to evasion attacks, such attacks have usually unrealistic requirements. Recent literature discussed the possibility to remove or not some of these requirements. This paper contributes to this literature by introducing a carpet-bombing patch attack which has almost no requirement. Targeting the feature representations, this patch attack does not require knowing the network task. This attack decreases accuracy on Imagenet, mAP on Pascal Voc, and IoU on Cityscapes without being aware that the underlying tasks involved classification, detection or semantic segmentation, respectively. Beyond the potential safety issues raised by this attack, the impact of the carpet-bombing attack highlights some interesting property of deep network layer dynamic.

cs.CV↗

arXiv2022

Riemannian data-dependent randomized smoothing for neural networks certification

Certification of neural networks is an important and challenging problem that has been attracting the attention of the machine learning community since few years. In this paper, we focus on randomized smoothing (RS) which is considered as the state-of-the-art method to obtain certifiably robust neural networks. In particular, a new data-dependent RS technique called ANCER introduced recently can be used to certify ellipses with orthogonal axis near each input data of the neural network. In this work, we remark that ANCER is not invariant under rotation of input data and propose a new rotationally-invariant formulation of it which can certify ellipses without constraints on their axis. Our approach called Riemannian Data Dependant Randomized Smoothing (RDDRS) relies on information geometry techniques on the manifold of covariance matrices and can certify bigger regions than ANCER based on our experiments on the MNIST dataset.

cs.LG↗