arXiv subjects

Yassine Maleh

Publications and source records attributed to Yassine Maleh.

12 recordsLinked to original sources

arXiv2026

Continual Visual Learning under Evolving Semantic Concept Shift

Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual systems, however, taxonomies, policies, and concept definitions can themselves evolve, causing the same visual evidence to require a different interpretation. We study this setting as evolving semantic concept shift and introduce SemReWrite, a framework for selectively updating obsolete visual--semantic mappings while preserving knowledge that remains valid. SemReWrite represents changes between old and revised semantic specifications, combines semantic discrepancy with sparse revised supervision to localize affected visual regions, and uses an input-dependent low-rank rewriting mechanism together with structured semantic memory, preservation, and obsolete-decision suppression. We further introduce EvoShift-Bench, spanning ImageNet, iNaturalist, CUB-200-2011, and DomainNet, with semantic transitions including class split, merge, boundary revision, insertion, partial redefinition, recurrence, and mixed semantic--appearance shift. To explicitly evaluate selective semantic revision, we introduce Rewrite Accuracy (RA) and Preservation Accuracy (PA) for affected and unaffected regions, respectively, Obsolete Retention (OR) for measuring residual outdated semantic associations, and the Selective Revision Score (SRS), which jointly summarizes rewriting and preservation performance. Experiments show that SemReWrite achieves a stronger balance between learning revised semantics and retaining unaffected knowledge than prompt replacement, conventional fine-tuning, parameter-efficient adaptation, and continual-learning strategies.

cs.CV↗

arXiv2026

Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates

Deployed machine learning systems face distribution drift, yet most monitoring pipelines stop at alarms and leave the response underspecified under labeling, compute, and latency constraints. We introduce Drift2Act, a drift-to-action controller that treats monitoring as constrained decision-making with explicit safety. Drift2Act combines a sensing layer that maps unlabeled monitoring signals to a belief over drift types with an active risk certificate that queries a small set of delayed labels from a recent window to produce an anytime-valid upper bound $U_t(δ)$ on current risk. The certificate gates operation: if $U_t(δ) \le τ$, the controller selects low-cost actions (e.g., recalibration or test-time adaptation); if $U_t(δ) > τ$, it activates abstain/handoff and escalates to rollback or retraining under cooldowns. In a realistic streaming protocol with label delay and explicit intervention costs, Drift2Act achieves near-zero safety violations and fast recovery at moderate cost on WILDS Camelyon17, DomainNet, and a controlled synthetic drift stream, outperforming alarm-only monitoring, adapt-always adaptation, schedule-based retraining, selective prediction alone, and an ablation without certification. Overall, online risk certification enables reliable drift response and reframes monitoring as decision-making with safety.

cs.LG↗

arXiv2026

SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML

Reliable uncertainty estimation is a key missing piece for on-device monitoring in TinyML: microcontrollers must detect failures, distribution shift, or accuracy drops under strict flash/latency budgets, yet common uncertainty approaches (deep ensembles, MC dropout, early exits, temporal buffering) typically require multiple passes, extra branches, or state that is impractical on milliwatt hardware. This paper proposes a novel and practical method, SNAP-UQ, for single-pass, label-free uncertainty estimation based on depth-wise next-activation prediction. SNAP-UQ taps a small set of backbone layers and uses tiny int8 heads to predict the mean and scale of the next activation from a low-rank projection of the previous one; the resulting standardized prediction error forms a depth-wise surprisal signal that is aggregated and mapped through a lightweight monotone calibrator into an actionable uncertainty score. The design introduces no temporal buffers or auxiliary exits and preserves state-free inference, while increasing deployment footprint by only a few tens of kilobytes. Across vision and audio backbones, SNAP-UQ reduces flash and latency relative to early-exit and deep-ensemble baselines (typically $\sim$40--60% smaller and $\sim$25--35% faster), with several competing methods at similar accuracy often exceeding MCU memory limits. On corrupted streams, it improves accuracy-drop event detection by multiple AUPRC points and maintains strong failure detection (AUROC $\approx 0.9$) in a single forward pass. By grounding uncertainty in layer-to-layer dynamics rather than solely in output confidence, SNAP-UQ offers a novel, resource-efficient basis for robust TinyML monitoring. Our code is available at: https://github.com/Ism-ail11/SNAP-UQ

cs.LG↗

arXiv2026

Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator

We introduce Simplex-FEM Networks (SiFEN), a learned piecewise-polynomial predictor that represents f: R^d -> R^k as a globally C^r finite-element field on a learned simplicial mesh in an optionally warped input space. Each query activates exactly one simplex and at most d+1 basis functions via barycentric coordinates, yielding explicit locality, controllable smoothness, and cache-friendly sparsity. SiFEN pairs degree-m Bernstein-Bezier polynomials with a light invertible warp and trains end-to-end with shape regularization, semi-discrete OT coverage, and differentiable edge flips. Under standard shape-regularity and bi-Lipschitz warp assumptions, SiFEN achieves the classic FEM approximation rate M^(-m/d) with M mesh vertices. Empirically, on synthetic approximation tasks, tabular regression/classification, and as a drop-in head on compact CNNs, SiFEN matches or surpasses MLPs and KANs at matched parameter budgets, improves calibration (lower ECE/Brier), and reduces inference latency due to geometric locality. These properties make SiFEN a compact, interpretable, and theoretically grounded alternative to dense MLPs and edge-spline networks.

cs.LG↗

arXiv2026

T3C: Test-Time Tensor Compression with Consistency Guarantees

We present T3C, a train-once, test-time budget-conditioned compression framework that exposes rank and precision as a controllable deployment knob. T3C combines elastic tensor factorization (maintained up to a maximal rank) with rank-tied mixed-precision quantization and a lightweight controller that maps a latency/energy/size budget token to per-layer rank/bit assignments; the policy snaps to hardware-aligned profiles and is monotone in the budget. A fast, layerwise consistency certificate, computed from spectral proxies and activation statistics, upper-bounds logit drift and regularizes training, yielding a practical reliability signal with negligible overhead. On ImageNet-1k, T3C shifts the vision Pareto frontier: for ResNet-50 at matched accuracy (\leq 0.5% drop), p50 latency is 1.18ms with a 38MB model, outperforming PTQ-8b (1.44ms, 88MB); for ViT-B/16, T3C reaches 2.30ms p50 with 59MB, improving over strong PTQ/QAT baselines. A single T3C checkpoint therefore provides predictable, certificate-backed accuracy-latency-size trade-offs on demand across devices.

cs.CL↗

arXiv2025

BayesQ: Uncertainty-Guided Bayesian Quantization

We present BayesQ, an uncertainty-guided post-training quantization framework that is the first to optimize quantization under the posterior expected loss. BayesQ fits a lightweight Gaussian posterior over weights (diagonal Laplace by default; optional K-FAC/low-rank), whitens by the posterior covariance, designs codebooks to minimize posterior-expected distortion, and allocates mixed precision via a greedy knapsack that maximizes marginal expected-loss reduction per bit under a global budget. For scalar quantizers, posterior-expected MSE yields closed-form tables; task-aware proxies are handled by short Monte Carlo on a small calibration set. An optional calibration-only distillation aligns the quantized model with the posterior predictive teacher. At matched average bits/weight of 3.0/3.5/4.0, BayesQ improves over strong PTQ baselines on ResNet-50 (ImageNet) and BERT-base (GLUE) e.g., vs. GPTQ by $+1.5/+0.7/+0.3$ top-1 percentage points on RN50 and $+1.1/+0.4/+0.2$ GLUE points on BERT, while requiring one-time preprocessing comparable to a GPTQ pass. BayesQ reframes low-bit quantization as uncertainty-aware risk minimization in a practical, post-training pipeline.

cs.LG↗

arXiv2025

TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML

We introduce TCUQ, a single pass, label free uncertainty monitor for streaming TinyML that converts short horizon temporal consistency captured via lightweight signals on posteriors and features into a calibrated risk score with an O(W ) ring buffer and O(1) per step updates. A streaming conformal layer turns this score into a budgeted accept/abstain rule, yielding calibrated behavior without online labels or extra forward passes. On microcontrollers, TCUQ fits comfortably on kilobyte scale devices and reduces footprint and latency versus early exit and deep ensembles (typically about 50 to 60% smaller and about 30 to 45% faster), while methods of similar accuracy often run out of memory. Under corrupted in distribution streams, TCUQ improves accuracy drop detection by 3 to 7 AUPRC points and reaches up to 0.86 AUPRC at high severities; for failure detection it attains up to 0.92 AUROC. These results show that temporal consistency, coupled with streaming conformal calibration, provides a practical and resource efficient foundation for on device monitoring in TinyML.

cs.LG↗

arXiv2024

BlockMEDC: Blockchain Smart Contracts for Securing Moroccan Higher Education Digital Certificates

Morocco's Vision 2030, known as Maroc Digital 2030, aims to position the country as a regional leader in digital technology by boosting digital infrastructure, fostering innovation, and advancing digital skills. Complementing this initiative, the Pacte ESRI 2030 strategy, launched in 2023, seeks to transform the higher education, research, and innovation sectors by integrating state-of-the-art digital technologies. In alignment with these national strategies, this paper introduces BlockMEDC, a blockchain-based system for securing and managing Moroccan educational digital certificates. Leveraging Ethereum smart contracts and the InterPlanetary File System, BlockMEDC automates the issuance, management, and verification of academic credentials across Moroccan universities. The proposed system addresses key issues such as document authenticity, manual verification, and lack of interoperability, delivering a secure, transparent, and cost-effective solution that aligns with Morocco's digital transformation goals for the education sector.

cs.CR↗

arXiv2024

Enhancing Bangla Fake News Detection Using Bidirectional Gated Recurrent Units and Deep Learning Techniques

The rise of fake news has made the need for effective detection methods, including in languages other than English, increasingly important. The study aims to address the challenges of Bangla which is considered a less important language. To this end, a complete dataset containing about 50,000 news items is proposed. Several deep learning models have been tested on this dataset, including the bidirectional gated recurrent unit (GRU), the long short-term memory (LSTM), the 1D convolutional neural network (CNN), and hybrid architectures. For this research, we assessed the efficacy of the model utilizing a range of useful measures, including recall, precision, F1 score, and accuracy. This was done by employing a big application. We carry out comprehensive trials to show the effectiveness of these models in identifying bogus news in Bangla, with the Bidirectional GRU model having a stunning accuracy of 99.16%. Our analysis highlights the importance of dataset balance and the need for continual improvement efforts to a substantial degree. This study makes a major contribution to the creation of Bangla fake news detecting systems with limited resources, thereby setting the stage for future improvements in the detection process.

cs.CL↗

arXiv2017

Study and Development of a Symmetric protocol to secure communications in WSN

Wireless Sensor Network (WSN) is consisting of independent and distributed sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. The most crucial and fundamental challenge facing WSN is security. Due to minimum capacity in-term of memory cost, processing and physical accessibility to sensors devices the security attacks are problematic. They are mostly deployed in open area, which expose them to different kinds of attacks. In this paper, we present an illustration of different attacks and vulnerabilities in WSN. Then we proposed a new lightweight cryptography algorithm for identifying compromised node in WSN called Leap Enhanced. Our evaluations on TOSSIM give a precise and detailed idea of the extra cost of consumption of resources needed to ensure the high level of expected security compared to other cryptography schemes in literature.

cs.CR↗

arXiv2016

Study and Development of a New Symmetric Key Management Scheme for Wireless Sensor Networks

Wireless Sensor Network (WSN) is consisting of independent and distributed sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. However, the limited resources of sensors and hostile environments in which they could be deployed, make this type of networks vulnerable to several types of attacks similar to those occurring in ad hoc networks. The most crucial and fundamental challenge that WSN is facing is security. The primary subject of all my work is to address this issue. Due to minimum capacity in term of memory cost, processing and physical accessibility to sensors devices the security attacks are problematic. They are mostly deployed in open area so are more exposed to different kinds of attacks. They must be designed in a way to successfully recover itself from different kinds of attacks. In this paper, we proposed a new lightweight cryptography algorithm based on LEAP+. Our evaluations on TOSSIM give a precise and detailed idea of the extra cost of consumption of resources needed to ensure the high level of expected security.

cs.CR↗

arXiv2016

An advanced Study on Cryptography Mechanisms for Wireless Sensor Networks

Wireless Sensor Network (WSN) is consisting of independent and distributed sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. The most crucial and fundamental challenge facing WSN is security. Due to minimum capacity in-term of memory cost, processing and physical accessibility to sensors devices the security attacks are problematic. They are mostly deployed in open area, which expose them to different kinds of attacks. In this paper, we present an illustration of different attacks and vulnerabilities in WSN. Then we describe and analyze security requirement, countermeasures based on cryptography mechanisms in literature. Finally, we present possible directions in future research.

cs.CR↗