arXiv subjects

David Naccache

Publications and source records attributed to David Naccache.

At least 19 recordsLinked to original sources

arXiv2026

Firmware Distribution as Attack Surface: A Security Study of ASIC Cryptocurrency Miners

ASIC cryptocurrency miners are a core component of blockchain infrastructures, directly converting computation and energy into monetary value. Despite their economic importance, their security is rarely evaluated in a structured manner. In this paper, we show that the firmware distribution ecosystem of mining devices fundamentally challenges existing trust assumptions. We introduce a scalable methodology based on the collection and static analysis of publicly distributed firmware artifacts, requiring neither device access nor runtime interaction. Applying this approach, we reconstruct and analyze 134 firmware images spanning manufacturers that account for over 99% of deployed miners (Bitmain, MicroBT, Canaan, Iceriver). Our results reveal that firmware artifacts alone are sufficient to recover internal architecture, identify security weaknesses, and reconstruct complete attack paths leading to high-impact adversarial objectives. In particular, our analysis reveals vulnerabilities that enable realistic large-scale attack scenarios, including firmware phishing and the exploitation of miners still operating over Stratum V1. Validation on two real devices confirms that publicly distributed artifacts closely reflect deployed software and that these weaknesses translate into attack capabilities. Overall, our study shows that firmware distribution mechanisms themselves constitute a primary attack surface, significantly lowering the barrier to compromise in the ASIC mining ecosystem.

cs.CR↗

arXiv2025

The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning

We present the design and results of the MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024, which focuses on federated learning (FL) for glioma sub-region segmentation in multi-parametric MRI and evaluates new weight aggregation methods aimed at improving robustness and efficiency. Six participating teams were evaluated using a standardized FL setup and a multi-institutional dataset derived from the BraTS glioma benchmark, consisting of 1,251 training cases, 219 validation cases, and 570 hidden test cases with segmentations for enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Teams were ranked using a cumulative scoring system that considered both segmentation performance, measured by Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95), and communication efficiency assessed through the convergence score. A PID-controller-based method achieved the top overall ranking, obtaining mean DSC values of 0.733, 0.761, and 0.751 for ET, TC, and WT, respectively, with corresponding HD95 values of 33.922 mm, 33.623 mm, and 32.309 mm, while also demonstrating the highest communication efficiency with a convergence score of 0.764. These findings advance the state of federated learning for medical imaging, surpassing top-performing methods from previous challenge iterations and highlighting PID controllers as effective mechanisms for stabilizing and optimizing weight aggregation in FL. The challenge code is available at https://github.com/FeTS-AI/Challenge.

cs.CV↗

arXiv2025

Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document

Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Character Recognition. Despite their effectiveness, these models are too costly for real-time or resource-constrained applications. We investigate model compression through knowledge distillation, training compact student models from a larger teacher. We leverage mechanistic interpretability to drive student architecture design within this framework. By analyzing internal computations, we identify essential subcomponents to retain, while having a clear view of which subcomponents should be approximated, skipped, or reparametrized based on their function. This approach yields Donut-MINT (Mechanistic Interpretability-based Network Trimming), a pruned Donut variant that reduces inference time and memory usage while maintaining strong performance on DocVQA, a standard benchmark for document Visual Question Answering. Our method reframes compression as circuit discovery, bridging interpretability research and practical Vision-Language Model deployment.

cs.CV↗

arXiv2025

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling

Variational Autoencoders (VAEs) with global priors trained under an imbalanced empirical class distribution can lead to underrepresentation of tail classes in the latent space. While $t^3$VAE improves robustness via heavy-tailed Student's $t$-distribution priors, its single global prior still allocates mass proportionally to class frequency. We address this latent geometric bias by introducing C-$t^3$VAE, which assigns a per-class Student's $t$ joint prior over latent and output variables. This design promotes uniform prior mass across class-conditioned components. To optimize our model we derive a closed-form objective from the $\gamma$-power divergence, and we introduce an equal-weight latent mixture for class-balanced generation. On SVHN-LT, CIFAR100-LT, and CelebA datasets, C-$t^3$VAE consistently attains lower FID scores than $t^3$VAE and Gaussian-based VAE baselines under severe class imbalance while remaining competitive in balanced or mildly imbalanced settings. In per-class F1 evaluations, our model outperforms the conditional Gaussian VAE across highly imbalanced settings. Moreover, we identify the mild imbalance threshold $\rho < 5$, for which Gaussian-based models remain competitive. However, for $\rho \geq 5$ our approach yields improved class-balanced generation and mode coverage.

cs.LG↗

arXiv2024

FedPID: An Aggregation Method for Federated Learning

This paper presents FedPID, our submission to the Federated Tumor Segmentation Challenge 2024 (FETS24). Inspired by FedCostWAvg and FedPIDAvg, our winning contributions to FETS21 and FETS2022, we propose an improved aggregation strategy for federated and collaborative learning. FedCostWAvg is a method that averages results by considering both the number of training samples in each group and how much the cost function decreased in the last round of training. This is similar to how the derivative part of a PID controller works. In FedPIDAvg, we also included the integral part that was missing. Another challenge we faced were vastly differing dataset sizes at each center. We solved this by assuming the sizes follow a Poisson distribution and adjusting the training iterations for each center accordingly. Essentially, this part of the method controls that outliers that require too much training time are less frequently used. Based on these contributions we now adapted FedPIDAvg by changing how the integral part is computed. Instead of integrating the loss function we measure the global drop in cost since the first round.

cs.LG↗

arXiv2024

CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models

Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly for self-supervised models. Most existing methods for generating saliency maps rely on ground truth labels, restricting their use to supervised tasks. EigenCAM is the only notable label-independent alternative, leveraging Singular Value Decomposition to generate saliency maps applicable across CNN models, but it does not fully exploit the tensorial structure of feature maps. In this work, we introduce the Tucker Saliency Map (TSM) method, which applies Tucker tensor decomposition to better capture the inherent structure of feature maps, producing more accurate singular vectors and values. These are used to generate high-fidelity saliency maps, effectively highlighting objects of interest in the input. We further extend EigenCAM and TSM into multivector variants -Multivec-EigenCAM and Multivector Tucker Saliency Maps (MTSM)- which utilize all singular vectors and values, further improving saliency map quality. Quantitative evaluations on supervised classification models demonstrate that TSM, Multivec-EigenCAM, and MTSM achieve competitive performance with label-dependent methods. Moreover, TSM enhances explainability by approximately 50% over EigenCAM for both supervised and self-supervised models. Multivec-EigenCAM and MTSM further advance state-of-the-art explainability performance on self-supervised models, with MTSM achieving the best results.

cs.CV↗

arXiv2023

Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts

In this study, we focus on sampling from the latent space of generative models built upon autoencoders so as the reconstructed samples are lifelike images. To do to, we introduce a novel post-training sampling algorithm rooted in the concept of probability mass functions, coupled with a quantization process. Our proposed algorithm establishes a vicinity around each latent vector from the input data and then proceeds to draw samples from these defined neighborhoods. This strategic approach ensures that the sampled latent vectors predominantly inhabit high-probability regions, which, in turn, can be effectively transformed into authentic real-world images. A noteworthy point of comparison for our sampling algorithm is the sampling technique based on Gaussian mixture models (GMM), owing to its inherent capability to represent clusters. Remarkably, we manage to improve the time complexity from the previous $\mathcal{O}(n\times d \times k \times i)$ associated with GMM sampling to a much more streamlined $\mathcal{O}(n\times d)$, thereby resulting in substantial speedup during runtime. Moreover, our experimental results, gauged through the Fr\'echet inception distance (FID) for image generation, underscore the superior performance of our sampling algorithm across a diverse range of models and datasets. On the MNIST benchmark dataset, our approach outperforms GMM sampling by yielding a noteworthy improvement of up to $0.89$ in FID value. Furthermore, when it comes to generating images of faces and ocular images, our approach showcases substantial enhancements with FID improvements of $1.69$ and $0.87$ respectively, as compared to GMM sampling, as evidenced on the CelebA and MOBIUS datasets. Lastly, we substantiate our methodology's efficacy in estimating latent space distributions in contrast to GMM sampling, particularly through the lens of the Wasserstein distance.

cs.LG↗

arXiv2023

The Balkans Continued Fraction

In a previous escapade we gave a collection of continued fractions involving Catalan's constant. This paper provides more general formulae governing those continued fractions. Having distinguished different cases associated to regions in the plan, we nickname those continued fractions \enquote{The Balkans} as they divide into areas which are related but still different in nature. Because we do not provide formal proofs of those machine-constructed formulae we do not claim them to be theorems. Still, each and every proposed formula was extensively tested numerically.

math.NT↗

arXiv2023

Simplex Autoencoders

Synthetic data generation is increasingly important due to privacy concerns. While Autoencoder-based approaches have been widely used for this purpose, sampling from their latent spaces can be challenging. Mixture models are currently the most efficient way to sample from these spaces. In this work, we propose a new approach that models the latent space of an Autoencoder as a simplex, allowing for a novel heuristic for determining the number of components in the mixture model. This heuristic is independent of the number of classes and produces comparable results. We also introduce a sampling method based on probability mass functions, taking advantage of the compactness of the latent space. We evaluate our approaches on a synthetic dataset and demonstrate their performance on three benchmark datasets: MNIST, CIFAR-10, and Celeba. Our approach achieves an image generation FID of 4.29, 13.55, and 11.90 on the MNIST, CIFAR-10, and Celeba datasets, respectively. The best AE FID results to date on those datasets are respectively 6.3, 85.3 and 35.6 we hence substantially improve those figures (the lower is the FID the better). However, AEs are not the best performing algorithms on the concerned datasets and all FID records are currently held by GANs. While we do not perform better than GANs on CIFAR and Celeba we do manage to squeeze-out a non-negligible improvement (of 0.21) over the current GAN-held record for the MNIST dataset.

cs.LG↗

arXiv2022

Pattern Recognition Experiments on Mathematical Expressions

We provide the results of pattern recognition experiments on mathematical expressions. We give a few examples of conjectured results. None of which was thoroughly checked for novelty. We did not attempt to prove all the relations found and focused on their generation.

math.NT↗

arXiv2022

A Note on the Ramanujan Machine

The Ramanujan Machine project detects new expressions related to constants of interest, such as $\zeta$ function values, $\gamma$ and algebraic numbers (to name a few). In particular the project lists a number of conjectures involving even and odd $\zeta$ function values, logarithms etc. We show that many relations detected by the Ramanujan Machine Project stem from a specific algebraic observation and show how to generate infinitely many. This provides an automated proof and/or an explanation of many of the relations listed as conjectures by the project (although not all of them).

math.NT↗

arXiv2022

On Catalan Constant Continued Fractions

The Ramanujan Machine project detects new expressions related to constants of interest, such as $\zeta$ function values, $\gamma$ and algebraic numbers (to name a few). In particular the project lists a number of conjectures concerning the Catalan constant $G= 0.91596559\ldots$ We show how to generate infinitely many. We used an ad hoc software toolchain and rather tedious mathematical developments. Because we do not provide a proper peer-reviewed proof of the relations given here we do not claim them to be theorems.

cs.SC↗

arXiv2022

A forensic analysis of the Google Home: repairing compressed data without error correction

This paper provides a detailed explanation of the steps taken to extract and repair a Google Home's internal data. Starting with reverse engineering the hardware of a commercial off-the-shelf Google Home, internal data is then extracted by desoldering and dumping the flash memory. As error correction is performed by the CPU using an undisclosed method, a new alternative method is shown to repair a corrupted SquashFS filesystem, under the assumption of a single or double bitflip per gzip-compressed fragment. Finally, a new method to handle multiple possible repairs using three-valued logic is presented.

cs.CR↗

arXiv2022

Automated Discovery of New $L$-Function Relations

$L$-functions typically encode interesting information about mathematical objects. This paper reports 29 identities between such functions that hitherto never appeared in the literature. Of these we have a complete proof for 9; all others are extensively numerically checked and we welcome proofs of their (in)validity. The method we devised to obtain these identities is a two-step process whereby a list of candidate identities is automatically generated, obtained, tested, and ultimately formally proven. The approach is however only \emph{semi-}automated as human intervention is necessary for the post-processing phase, to determine the most general form of a conjectured identity and to provide a proof for them. This work complements other instances in the literature where automated symbolic computation has served as a productive step toward theorem proving and can be extended in several directions further to explore the algebraic landscape of $L$-functions and similar constructions.

math.NT↗

arXiv2022

FedControl: When Control Theory Meets Federated Learning

To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters. We depart from this approach by differentiating client contributions according to the performance of local learning and its evolution. The technique is inspired from control theory and its classification performance is evaluated extensively in IID framework and compared with FedAvg.

cs.LG↗

arXiv2022

Federated Learning Aggregation: New Robust Algorithms with Guarantees

Federated Learning has been recently proposed for distributed model training at the edge. The principle of this approach is to aggregate models learned on distributed clients to obtain a new more general "average" model (FedAvg). The resulting model is then redistributed to clients for further training. To date, the most popular federated learning algorithm uses coordinate-wise averaging of the model parameters for aggregation. In this paper, we carry out a complete general mathematical convergence analysis to evaluate aggregation strategies in a federated learning framework. From this, we derive novel aggregation algorithms which are able to modify their model architecture by differentiating client contributions according to the value of their losses. Moreover, we go beyond the assumptions introduced in theory, by evaluating the performance of these strategies and by comparing them with the one of FedAvg in classification tasks in both the IID and the Non-IID framework without additional hypothesis.

stat.ML↗

arXiv2021

Noise-Resilient Ensemble Learning using Evidence Accumulation Clustering

Ensemble Learning methods combine multiple algorithms performing the same task to build a group with superior quality. These systems are well adapted to the distributed setup, where each peer or machine of the network hosts one algorithm and communicate its results to its peers. Ensemble learning methods are naturally resilient to the absence of several peers thanks to the ensemble redundancy. However, the network can be corrupted, altering the prediction accuracy of a peer, which has a deleterious effect on the ensemble quality. In this paper, we propose a noise-resilient ensemble classification method, which helps to improve accuracy and correct random errors. The approach is inspired by Evidence Accumulation Clustering , adapted to classification ensembles. We compared it to the naive voter model over four multi-class datasets. Our model showed a greater resilience, allowing us to recover prediction under a very high noise level. In addition as the method is based on the evidence accumulation clustering, our method is highly flexible as it can combines classifiers with different label definitions.

cs.LG↗

arXiv2021

Tagged Documents Co-Clustering

Tags are short sequences of words allowing to describe textual and non-texual resources such as as music, image or book. Tags could be used by machine information retrieval systems to access quickly a document. These tags can be used to build recommender systems to suggest similar items to a user. However, the number of tags per document is limited, and often distributed according to a Zipf law. In this paper, we propose a methodology to cluster tags into conceptual groups. Data are preprocessed to remove power-law effects and enhance the context of low-frequency words. Then, a hierarchical agglomerative co-clustering algorithm is proposed to group together the most related tags into clusters. The capabilities were evaluated on a sparse synthetic dataset and a real-world tag collection associated with scientific papers. The task being unsupervised, we propose some stopping criterion for selectecting an optimal partitioning.

cs.IR↗