arXiv subjects

Mohamed Aly Bouke

Publications and source records attributed to Mohamed Aly Bouke.

10 recordsLinked to original sources

arXiv2026

Multi-Level Distributional Entropy from Flow Summary Statistics for Explainable Network Intrusion Detection

Machine learning network intrusion detection systems (IDS) operate on aggregate flow statistics that discard the distributional structure of traffic, and although information-theoretic measures capture that structure, established entropy estimators require raw packet sequences that pre-aggregated flow datasets do not contain. No prior method derives entropy from the summary statistics those records already hold. We introduce Multi-Level Distributional Entropy (MDE), which computes interpretable information-theoretic features analytically from flow-level summary statistics at three levels, within-flow Gaussian differential entropy, cross-directional Jensen-Shannon divergence (JSD), and Transmission Control Protocol (TCP) flag-incidence Shannon entropy, with closed-form properties and no raw packet access; only imputation medians and score bounds are fitted on the training split. We pair the features with a leakage-free, fold-local evaluation protocol that reports the full operational metric suite across cross-validation, temporal, pseudo-live, cross-dataset, and unseen-attack-family settings, on four benchmarks (NSL-KDD, CICIDS-2017, CICIDS-2018, UNSW-NB15) with tree-ensemble classifiers and SHAP. The protocol exposes failure modes that aggregate weighted F1 conceals: on CICIDS-2018 an F1 of 0.73 hides a detection rate (DR) of 0.44, on held-out attack families F1 exceeds 0.998 while DR falls to zero, and a 703K-flow pseudo-live replay reveals a threshold-ranking divergence in which score ranking is largely preserved (area under the ROC curve, AUC, 0.84 to 0.86) while fixed-threshold detection collapses (DR 0.08). The entropy features match conventional features within 0.1 percentage points of F1 and receive reproducible SHAP attributions (Spearman 0.84 to 0.94), so their contribution is a grounded, interpretable representation and an evaluation methodology rather than an accuracy gain.

cs.CR↗

arXiv2026

Sentence-Level Context Sensitivity as a Training-Free Detector of Unsupported Content, Evaluated Against Trained Verifiers

Retrieval-augmented generation (RAG) assistants summarize records in clinical and legal work, where one unsupported sentence can mislead a reader. The contrast between an output's likelihood with and without its source is an established faithfulness score for whole summaries and answers, but it has not been measured as a detector of the individual unsupported sentence in multi-passage RAG answers, against trained verifiers, or for its cost. We implement it as a training-free detector that re-scores a fixed answer under the full context, no context, and each chunk removed, and returns the chunk whose removal lowers a sentence's likelihood most as a candidate supporting passage. We evaluate it on RAGTruth, TofuEval, and RAGBench with six scorers and against five verifiers, up to a large language model (LLM) judge, on identical inputs under a source-level split. Scoring per sentence ranks unsupported sentences better than the answer-level form of the same signal on all three benchmarks, by 0.033 to 0.071 in the area under the receiver operating characteristic curve (AUC). On RAGTruth the training-free score reaches an AUC of 0.717 to 0.745 across scorers and 0.773 with a classifier, above entailment and attribution baselines and level with per-chunk fact-checkers, at about one forty-seventh of the LLM judge's compute on a 1.5B scorer, while a full-context fact-checker and the judge are more accurate and are not improved by it. The signal is weakest on short-answer question answering, where the scorer can answer from memory.

cs.CL↗

arXiv2026

A Competing-Hazards Systematization of Loss of Control in Autonomous Agents

Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of human control. Yet incident reports and agent-safety evaluations describe these events differently, making it difficult to compare failures, trace risk across attempts, or separate agent behavior from the environment's role in allowing an out-of-scope action to succeed. To address this gap, we introduce a common framework in which each attempt ends in approved completion, safe stopping, scope escape, or continuation. We formalize the framework as a discrete-time competing-hazards model and derive escape probability within a retry budget, a model-conditional safe-budget limit, and conditions for estimation from execution logs. We audit 22 incident reports and 102 agent-safety evaluations published from January 2025 to September 2026 using primary sources. Six incidents involved tasks that could not be completed within scope, thirteen involved agents that continued rather than stopped, and five did not report stopping behavior. Developers' figures imply a task-level incidence ratio near 47 for out-of-scope coordination in never-solved versus solved tasks. Among evaluations, 87 recorded an out-of-scope effect or specification violation, 26 treated safe stopping as a first-class outcome, only 20 recorded both, and 79 merged budget exhaustion with failure. In 20 of 22 incidents, the environment allowed an out-of-scope effect, indicating that realized loss of control often reflected persistent agent behavior interacting with permissive boundary conditions; meanwhile, no evaluation reported all fields needed to estimate the full competing-hazards process from published evidence.

cs.AI↗

arXiv2026

A Global Readiness and Sovereignty Capability Model for Post-Quantum Cryptography Migration

Cryptographic dependence predates the quantum era, but the migration to post-quantum cryptography (PQC) opens a rare window to reshape it, because the algorithms, implementations, hardware, and standards adopted now can lock in dependence or sovereignty for decades. This paper introduces the Readiness-Sovereignty Capability Model (RSCM), a national measurement model that operationalizes PQC readiness together with cryptographic sovereignty, which current maturity models score only as readiness and the sovereignty literature defines without measuring. RSCM decomposes sovereignty into three distinct constructs, indigenous cryptographic capacity, indigenous post-quantum control, and external dependency, and certifies a post-quantum maker only through a gate requiring demonstrated, institutionally sustained creation in at least one core layer, whether design, implementation, or validation. Applying it to fifty-seven documented cryptographic actors coded from cited public evidence, and testing that coding with an independent second coder, a plausible-state bootstrap, and convergent-validity checks, we find that twenty countries clear the gate, fifteen as full-stack makers and five as research makers, eleven hold strong general capacity without post-quantum control, one is a ready adopter, and twenty-five are dependent. The gate cells show substantial weighted agreement, a quadratic-weighted kappa of 0.71, and the maker classification is stable in its core though uncertain at the threshold. Readiness tracks independent cyber indices at rank correlations up to 0.70, while post-quantum creation shows no significant correlation with the commitment index, a rank correlation of only 0.22 that separates control from readiness. The paper contributes the framework, the evidence-graded assessment, and policy directions for building indigenous quantum-safe capacity.

cs.CR↗

arXiv2025

The Hashed Fractal Key Recovery (HFKR) Problem: From Symbolic Path Inversion to Post-Quantum Cryptographic Keys

Classical cryptographic systems rely heavily on structured algebraic problems, such as factorization, discrete logarithms, or lattice-based assumptions, which are increasingly vulnerable to quantum attacks and structural cryptanalysis. In response, this work introduces the Hashed Fractal Key Recovery (HFKR) problem, a non-algebraic cryptographic construction grounded in symbolic dynamics and chaotic perturbations. HFKR builds on the Symbolic Path Inversion Problem (SPIP), leveraging symbolic trajectories generated via contractive affine maps over $\mathbb{Z}^2$, and compressing them into fixed-length cryptographic keys using hash-based obfuscation. A key contribution of this paper is the empirical confirmation that these symbolic paths exhibit fractal behavior, quantified via box counting dimension, path geometry, and spatial density measures. The observed fractal dimension increases with trajectory length and stabilizes near 1.06, indicating symbolic self-similarity and space-filling complexity, both of which reinforce the entropy foundation of the scheme. Experimental results across 250 perturbation trials show that SHA3-512 and SHAKE256 amplify symbolic divergence effectively, achieving mean Hamming distances near 255, ideal bit-flip rates, and negligible entropy deviation. In contrast, BLAKE3 exhibits statistically uniform but weaker diffusion. These findings confirm that HFKR post-quantum security arises from the synergy between symbolic fractality and hash-based entropy amplification. The resulting construction offers a lightweight, structure-free foundation for secure key generation in adversarial settings without relying on algebraic hardness assumptions.

cs.CR↗

arXiv2025

On the Intractability of Chaotic Symbolic Walks: Toward a Non-Algebraic Post-Quantum Hardness Assumption

Most classical and post-quantum cryptographic assumptions, including integer factorization, discrete logarithms, and Learning with Errors (LWE), rely on algebraic structures such as rings or vector spaces. While mathematically powerful, these structures can be exploited by quantum algorithms or advanced algebraic attacks, raising a pressing need for structure-free alternatives. To address this gap, we introduce the Symbolic Path Inversion Problem (SPIP), a new computational hardness assumption based on symbolic trajectories generated by contractive affine maps with bounded noise over Z2. Unlike traditional systems, SPIP is inherently non-algebraic and relies on chaotic symbolic evolution and rounding-induced non-injectivity to render inversion computationally infeasible. We prove that SPIP is PSPACE-hard and #P-hard, and demonstrate through empirical simulation that even short symbolic sequences (e.g., n = 3, m = 2) can produce over 500 valid trajectories for a single endpoint, with exponential growth reaching 2256 paths for moderate parameters. A quantum security analysis further shows that Grover-style search offers no practical advantage due to oracle ambiguity and verification instability. These results position SPIP as a viable foundation for post-quantum cryptography that avoids the vulnerabilities of algebraic symmetry while offering scalability, unpredictability, and resistance to both classical and quantum inversion.

cs.CR↗

arXiv2025

Fractal Attractors in Random Nonlinear Iterated Function Systems: Existence, Stability, and Dimensional Properties

This study develops a comprehensive theoretical and computational framework for Random Nonlinear Iterated Function Systems (RNIFS), a generalization of classical IFS models that incorporates both nonlinearity and stochasticity. We establish mathematical guarantees for the existence and stability of invariant fractal attractors by leveraging contractivity conditions, Lyapunov-type criteria, and measure-theoretic arguments. Empirically, we design a set of high-resolution simulations across diverse nonlinear functions and probabilistic schemes to analyze the emergent attractors geometry and dimensionality. A box-counting method is used to estimate the fractal dimension, revealing attractors with rich internal structure and dimensions ranging from 1.4 to 1.89. Additionally, we present a case study comparing RNIFS to the classical Sierpiński triangle, demonstrating the generalization's ability to preserve global shape while enhancing geometric complexity. These findings affirm the capacity of RNIFS to model intricate, self-similar structures beyond the reach of traditional deterministic systems, offering new directions for the study of random fractals in both theory and applications.

math.DS↗

arXiv2025

The Theory of the Unique Latent Pattern: A Formal Epistemic Framework for Structural Singularity in Complex Systems

This paper introduces the Theory of the Unique Latent Pattern (ULP), a formal epistemic framework that redefines the origin of apparent complexity in dynamic systems. Rather than attributing unpredictability to intrinsic randomness or emergent nonlinearity, ULP asserts that every analyzable system is governed by a structurally unique, deterministic generative mechanism, one that remains hidden not due to ontological indeterminacy, but due to epistemic constraints. The theory is formalized using a non-universal generative mapping $ \mathcal{F}_S(P_S, t) $, where each system $ S $ possesses its own latent structure $ P_S $, irreducible and non-replicable across systems. Observed irregularities are modeled as projections of this generative map through observer-limited interfaces, introducing epistemic noise $ \varepsilon_S(t) $ as a measure of incomplete access. By shifting the locus of uncertainty from the system to the observer, ULP reframes chaos as a context-relative failure of representation. We contrast this position with foundational paradigms in chaos theory, complexity science, and statistical learning. While they assume or model shared randomness or collective emergence, ULP maintains that every instance harbors a singular structural identity. Although conceptual, the theory satisfies the criterion of falsifiability in the Popperian sense, it invites empirical challenge by asserting that no two systems governed by distinct latent mechanisms will remain indistinguishable under sufficient resolution. This opens avenues for structurally individuated models in AI, behavioral inference, and epistemic diagnostics.

cs.AI↗

arXiv2025

Data Dams: A Novel Framework for Regulating and Managing Data Flow in Large-Scale Systems

In the era of big data, managing dynamic data flows efficiently is crucial as traditional storage models struggle with real-time regulation and risk overflow. This paper introduces Data Dams, a novel framework designed to optimize data inflow, storage, and outflow by dynamically adjusting flow rates to prevent congestion while maximizing resource utilization. Inspired by physical dam mechanisms, the framework employs intelligent sluice controls and predictive analytics to regulate data flow based on system conditions such as bandwidth availability, processing capacity, and security constraints. Simulation results demonstrate that the Data Dam significantly reduces average storage levels (371.68 vs. 426.27 units) and increases total outflow (7999.99 vs. 7748.76 units) compared to static baseline models. By ensuring stable and adaptive outflow rates under fluctuating data loads, this approach enhances system efficiency, mitigates overflow risks, and outperforms existing static flow control strategies. The proposed framework presents a scalable solution for dynamic data management in large-scale distributed systems, paving the way for more resilient and efficient real-time processing architectures.

cs.IR↗

arXiv2025

Entropy Mixing Networks: Enhancing Pseudo-Random Number Generators with Lightweight Dynamic Entropy Injection

Random number generation plays a vital role in cryptographic systems and computational applications, where uniformity, unpredictability, and robustness are essential. This paper presents the Entropy Mixing Network (EMN), a novel hybrid random number generator designed to enhance randomness quality by combining deterministic pseudo-random generation with periodic entropy injection. To evaluate its effectiveness, we propose a comprehensive assessment framework that integrates statistical tests, advanced metrics, and visual analyses, providing a holistic view of randomness quality, predictability, and computational efficiency. The results demonstrate that EMN outperforms Python's SystemRandom and MersenneTwister in critical metrics, achieving the highest Chi-squared p-value (0.9430), entropy (7.9840), and lowest predictability (-0.0286). These improvements come with a trade-off in computational performance, as EMN incurs a higher generation time (0.2602 seconds). Despite this, its superior randomness quality makes it particularly suitable for cryptographic applications where security is prioritized over speed.

cs.CR↗