arXiv subjects

Jérémie Boulanger

Publications and source records attributed to Jérémie Boulanger.

10 recordsLinked to original sources

arXiv2026

DinoLizer: Separating VAE and Diffusion Artifacts in Generative Inpainting Localization

We introduce DinoLizer, a DINOv2-based localizer of manipulated areas in generative inpainting. The model is trained to focus on semantically altered regions by treating reconstructed areas outside the inpainted mask as a separate class, which yields significant improvements w.r.t. the conven- tional approach. We train the model with LORA on the Query and Value of the transformer blocks and simply add 1 linear layer on top of the backbone to predict manipulations on a 14 x 14 patch resolution. Because DINOv2 only accepts fixed- sized images, we use a sliding window approach to aggregate the predictions on larger images. Empirical results show that DinoLizer outperforms state-of-the-art methods on our proposed dataset and SOTA inpainting datasets. Furthermore, it is very robust to JPEG (double) compression. On average, DinoLizer achieves a 20% higher Intersection over Union score compared to the second best model. The code is publicly available here: https://github.com/anonyme610/dinolizer.

cs.CV↗

arXiv2026

Tackle CSM in JPEG Steganalysis with Data Adaptation

Steganalysis models excel on benchmark datasets but struggle in the wild when analyzed images are produced by a processing pipeline unseen during training. This problem known as Cover Source Mismatch (CSM) is particularly hard in realistic settings where practitioners (1) have access to only a small, unlabeled dataset, (2) are unsure of the processing techniques applied to these images, and (3) lack information on the proportion of covers and stegos in that set. To answer this challenge, we introduce TADA (Target Alignment through Data Adaptation), a framework learning to emulate the unknown processing pipeline from a small unlabeled target set. This architecture is trained with a loss combining residual covariance alignment, residual distribution matching, and a $\ell^2$ loss constraining the emulator to produce realistic images. Across toy and operational targets, TADA yields substantial gains in robustness to CSM and improves operational generalization compared to strong holistic and atomistic baselines. Additional resources are available at this link: https://github.com/RonyAbecidan/TADA

eess.IV↗

arXiv2025

Time and covariance smoothing for restoration of bivariate signals

In many applications and physical phenomena, bivariate signals are polarized, i.e. they trace an elliptical trajectory over time when viewed in the 2D planes of their two components. The smooth evolution of this elliptical trajectory, called polarization ellipse, is highly informative to solve ill-posed inverse problems involving bivariate signals where the signal is collected through indirect, noisy or incomplete measurements. This work proposes a novel formulation and an efficient algorithm for reconstructing bivariate signals with polarization regularization. The proposed formulation leverages the compact representation of polarization through the instantaneous covariance matrices. To address the resulting quartic optimization problem, we propose a well-suited parameter splitting strategy which leads to an efficient iterative algorithm (alternating direction method of multipliers (ADMM)) with convex subproblems at each iteration. The performance of the proposed method is illustrated on numerical synthetic data experiments.

eess.SP↗

arXiv2025

Denoising bivariate signals via smoothing and polarization priors

We propose two formulations to leverage the geometric properties of bivariate signals for dealing with the denoising problem. In doing so, we use the instantaneous Stokes parameters to incorporate the polarization state of the signal. While the first formulation exploits the statistics of the Stokes representation in a Bayesian setting, the second uses a kernel regression formulation to impose locally smooth time-varying polarization properties. In turn, we obtain two formulations that allow us to use both signal and polarization domain regularization for denoising a bivariate signal. The solutions to them exploit the polarization information efficiently as demonstrated in the numerical simulations

eess.SP↗

arXiv2024

Blind Data Adaptation to tackle Covariate Shift in Operational Steganalysis

The proliferation of image manipulation for unethical purposes poses significant challenges in social networks. One particularly concerning method is Image Steganography, allowing individuals to hide illegal information in digital images without arousing suspicions. Such a technique pose severe security risks, making it crucial to develop effective steganalysis methods enabling to detect manipulated images for clandestine communications. Although significant advancements have been achieved with machine learning models, a critical issue remains: the disparity between the controlled datasets used to train steganalysis models against real-world datasets of forensic practitioners, undermining severely the practical effectiveness of standardized steganalysis models. In this paper, we address this issue focusing on a realistic scenario where practitioners lack crucial information about the limited target set of images under analysis, including details about their development process and even whereas it contains manipulated images or not. By leveraging geometric alignment and distribution matching of source and target residuals, we develop TADA (Target Alignment through Data Adaptation), a novel methodology enabling to emulate sources aligned with specific targets in steganalysis, which is also relevant for highly unbalanced targets. The emulator is represented by a light convolutional network trained to align distributions of image residuals. Experimental validation demonstrates the potential of our strategy over traditional methods fighting covariate shift in steganalysis.

eess.IV↗

arXiv2023

Using Set Covering to Generate Databases for Holistic Steganalysis

Within an operational framework, covers used by a steganographer are likely to come from different sensors and different processing pipelines than the ones used by researchers for training their steganalysis models. Thus, a performance gap is unavoidable when it comes to out-of-distributions covers, an extremely frequent scenario called Cover Source Mismatch (CSM). Here, we explore a grid of processing pipelines to study the origins of CSM, to better understand it, and to better tackle it. A set-covering greedy algorithm is used to select representative pipelines minimizing the maximum regret between the representative and the pipelines within the set. Our main contribution is a methodology for generating relevant bases able to tackle operational CSM. Experimental validation highlights that, for a given number of training samples, our set covering selection is a better strategy than selecting random pipelines or using all the available pipelines. Our analysis also shows that parameters as denoising, sharpening, and downsampling are very important to foster diversity. Finally, different benchmarks for classical and wild databases show the good generalization property of the extracted databases. Additional resources are available at github.com/RonyAbecidan/HolisticSteganalysisWithSetCovering.

cs.MM↗

arXiv2023

Leveraging Data Geometry to Mitigate CSM in Steganalysis

In operational scenarios, steganographers use sets of covers from various sensors and processing pipelines that differ significantly from those used by researchers to train steganalysis models. This leads to an inevitable performance gap when dealing with out-of-distribution covers, commonly referred to as Cover Source Mismatch (CSM). In this study, we consider the scenario where test images are processed using the same pipeline. However, knowledge regarding both the labels and the balance between cover and stego is missing. Our objective is to identify a training dataset that allows for maximum generalization to our target. By exploring a grid of processing pipelines fostering CSM, we discovered a geometrical metric based on the chordal distance between subspaces spanned by DCTr features, that exhibits high correlation with operational regret while being not affected by the cover-stego balance. Our contribution lies in the development of a strategy that enables the selection or derivation of customized training datasets, enhancing the overall generalization performance for a given target. Experimental validation highlights that our geometry-based optimization strategy outperforms traditional atomistic methods given reasonable assumptions. Additional resources are available at github.com/RonyAbecidan/LeveragingGeometrytoMitigateCSM.

cs.LG↗

arXiv2015

Automatic sensor-based detection and classification of climbing activities

This article presents a method to automatically detect and classify climbing activities using inertial measurement units (IMUs) attached to the wrists, feet and pelvis of the climber. The IMUs record limb acceleration and angular velocity. Detection requires a learning phase with manual annotation to construct the statistical models used in the cusum algorithm. Full-body activity is then classified based on the detection of each IMU.

stat.AP↗

arXiv2012

Stochastic description of geometric phase for polarized waves in random media

We present a stochastic description of multiple scattering of polarized waves in the regime of forward scattering. In this regime, if the source is polarized, polarization survives along a few transport mean free paths, making it possible to measure an outgoing polarization distribution. We solve the direct problem using compound Poisson processes on the rotation group SO(3) and non-commutative harmonic analysis. The obtained solution generalizes previous works in multiple scattering theory and is used to design an algorithm solving the inverse problem of estimating the scattering properties of the medium from the observations. This technique applies to thin disordered layers, spatially fluctuating media and multiple scattering systems and is based on the polarization but not on the signal amplitude. We suggest that it can be used as a non invasive testing method.

physics.data-an↗

arXiv2012

Observation of a non-adiabatic geometric phase for elastic waves

We report the experimental observation of a geometric phase for elastic waves in a waveguide with helical shape. The setup reproduces the experiment by Tomita and Chiao [A. Tomita, R.Y. Chiao, Phys. Rev. Lett. 57 (1986) 937-940, 2471] that showed first evidence of a Berry phase, a geometric phase for adiabatic time evolution, in optics. Experimental evidence of a non-adiabatic geometric phase has been reported in quantum mechanics. We have performed an experiment to observe the polarization transport of classical elastic waves. In a waveguide, these waves are polarized and dispersive. Whereas the wavelength is of the same order of magnitude as the helix's radius, no frequency dependent correction is necessary to account for the theoretical prediction. This shows that in this regime, the geometric phase results directly from geometry and not from a correction to an adiabatic phase.

physics.class-ph↗