Selected work

Representative Papers

Multi-Level Distributional Entropy for Explainable Network Intrusion Detection

Jun 29, 2026

This work addresses the limitations of existing network intrusion detection systems that rely on aggregated flow statistics, which discard distributional structure, and conventional entropy-based methods that require raw packets and are thus inapplicable to pre-aggregated data. The authors propose a Multilevel Distributional Entropy (MDE) framework that, for the first time, directly constructs interpretable, multilayer entropy features from flow-level summary statistics—specifically, intra-flow Gaussian differential entropy, inter-directional Jensen–Shannon divergence, and TCP flag Shannon entropy—without needing raw packets or training samples. Evaluated on four benchmark datasets, MDE alone achieves weighted F1 scores ranging from 0.708 to 0.989. SHAP analysis demonstrates high feature stability (Spearman ρ = 0.80–0.95) and reveals that fixed thresholds suffer severe performance degradation under temporal shifts, with detection rates plummeting to 0.082, thereby substantially enhancing detection transparency and robustness.

0 citationsRead paper

A Comparative Study of Penalised, Bayesian, Spatial, and Tree-Based Models for Provincial Poverty in Indonesia: Small Samples and High Collinearity

Apr 07, 2026

This study addresses the challenges of analyzing provincial poverty in Indonesia, where a small sample size (n = 34) and high-dimensional multicollinearity undermine the stability of conventional regression models. To tackle this, the authors develop a systematic comparative framework evaluating several regularization and machine learning approaches—including ridge regression, LASSO, elastic net, Bayesian shrinkage priors, spatial ICAR, and Bayesian additive regression trees (BART)—in terms of predictive performance and robustness. The results demonstrate that parametric linear shrinkage methods, particularly ridge regression, yield the most accurate and stable predictions, whereas more complex ensemble models tend to overfit. Notably, ICT skills emerge as a consistently significant negative predictor of poverty across all well-performing models, highlighting their potential as a strategic priority for development policy. This work offers a reliable modeling paradigm and empirical foundation for evidence-based policymaking in data-scarce settings.

0 citationsRead paper

Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection

Apr 01, 2026

Neuropsychiatric symptoms in late life are difficult to distinguish from early signs of Alzheimer’s disease (AD), limiting their utility as biomarkers. This study proposes a deep learning normative model based on structural MRI that leverages a 3D convolutional neural network to map brain structure to Neuropsychiatric Inventory Questionnaire (NPI-Q) scores in cognitively stable individuals. The deviation between observed and predicted NPI-Q scores—termed DNPI—is introduced as a non-invasive indicator of early AD risk. Results demonstrate that DNPI significantly predicts future conversion to AD (adjusted odds ratio = 2.5, p < 0.01), with predictive performance (AUC = 0.74) comparable to that of cerebrospinal fluid Aβ42 (AUC = 0.75), thereby overcoming key limitations of conventional cognitive assessments.

0 citationsRead paper

KARIPAP: Quantum-Inspired Tensor Network Compression of Large Language Models Using Infinite Projected Entangled Pair States and Tensor Renormalization Group

Oct 22, 2025

To address the high computational cost, energy consumption, and deployment constraints arising from the massive parameter counts of large language models (LLMs), this work proposes a quantum-inspired tensor network compression framework. We introduce two-dimensional infinite projected entangled pair states (iPEPS) — for the first time applied to LLM compression — to model the multi-directional quantum entanglement structure inherent in attention mechanisms and across Transformer layers, thereby revealing their intrinsic low-dimensional entanglement manifold. Leveraging tensor renormalization group (TRG) methods, we achieve polynomial-time efficient tensor contraction and identify redundant parameters via inter-layer entanglement analysis. Evaluated on LLaMA-2 7B, our method attains 93% memory reduction, 70% parameter pruning, and 50% and 25% speedups in training and inference, respectively, with only a 2–3% accuracy degradation. This establishes a novel paradigm for scalable, energy-efficient, quantum-aware AI architectures.

0 citationsRead paper

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

Jun 04, 2025

Traditional algebraic cryptosystems (e.g., RSA, ECC, lattice-based schemes) exhibit vulnerabilities under quantum attacks and structural cryptanalysis. Method: This paper proposes HFKR, a structure-free, quantum-resistant key generation scheme. It employs contraction-affine mappings over ℤ² to generate chaotic symbolic trajectories; characterizes their self-similarity and space-filling complexity via fractal dimension (empirically ≈1.06); and applies SHA3-512/SHAKE256 hashing for entropy amplification and chaotic parameter perturbation. Results: Under 250 perturbations, generated keys achieve a mean Hamming distance of 255, near-ideal bit-flip rates, and negligible entropy deviation; BLAKE3 underperforms due to insufficient diffusion. This work pioneers the rigorous integration of fractal geometry with cryptographic entropy modeling, establishing a lightweight, algebraically unstructured, and provably quantum-resistant paradigm.

0 citationsRead paper

Recent publications

Latest Papers

Multi-Level Distributional Entropy for Explainable Network Intrusion Detection

Jun 29, 2026

This work addresses the limitations of existing network intrusion detection systems that rely on aggregated flow statistics, which discard distributional structure, and conventional entropy-based methods that require raw packets and are thus inapplicable to pre-aggregated data. The authors propose a Multilevel Distributional Entropy (MDE) framework that, for the first time, directly constructs interpretable, multilayer entropy features from flow-level summary statistics—specifically, intra-flow Gaussian differential entropy, inter-directional Jensen–Shannon divergence, and TCP flag Shannon entropy—without needing raw packets or training samples. Evaluated on four benchmark datasets, MDE alone achieves weighted F1 scores ranging from 0.708 to 0.989. SHAP analysis demonstrates high feature stability (Spearman ρ = 0.80–0.95) and reveals that fixed thresholds suffer severe performance degradation under temporal shifts, with detection rates plummeting to 0.082, thereby substantially enhancing detection transparency and robustness.

0 citationsRead paper

A Comparative Study of Penalised, Bayesian, Spatial, and Tree-Based Models for Provincial Poverty in Indonesia: Small Samples and High Collinearity

Apr 07, 2026

This study addresses the challenges of analyzing provincial poverty in Indonesia, where a small sample size (n = 34) and high-dimensional multicollinearity undermine the stability of conventional regression models. To tackle this, the authors develop a systematic comparative framework evaluating several regularization and machine learning approaches—including ridge regression, LASSO, elastic net, Bayesian shrinkage priors, spatial ICAR, and Bayesian additive regression trees (BART)—in terms of predictive performance and robustness. The results demonstrate that parametric linear shrinkage methods, particularly ridge regression, yield the most accurate and stable predictions, whereas more complex ensemble models tend to overfit. Notably, ICT skills emerge as a consistently significant negative predictor of poverty across all well-performing models, highlighting their potential as a strategic priority for development policy. This work offers a reliable modeling paradigm and empirical foundation for evidence-based policymaking in data-scarce settings.

0 citationsRead paper

Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection

Apr 01, 2026

Neuropsychiatric symptoms in late life are difficult to distinguish from early signs of Alzheimer’s disease (AD), limiting their utility as biomarkers. This study proposes a deep learning normative model based on structural MRI that leverages a 3D convolutional neural network to map brain structure to Neuropsychiatric Inventory Questionnaire (NPI-Q) scores in cognitively stable individuals. The deviation between observed and predicted NPI-Q scores—termed DNPI—is introduced as a non-invasive indicator of early AD risk. Results demonstrate that DNPI significantly predicts future conversion to AD (adjusted odds ratio = 2.5, p < 0.01), with predictive performance (AUC = 0.74) comparable to that of cerebrospinal fluid Aβ42 (AUC = 0.75), thereby overcoming key limitations of conventional cognitive assessments.

0 citationsRead paper

KARIPAP: Quantum-Inspired Tensor Network Compression of Large Language Models Using Infinite Projected Entangled Pair States and Tensor Renormalization Group

Oct 22, 2025

To address the high computational cost, energy consumption, and deployment constraints arising from the massive parameter counts of large language models (LLMs), this work proposes a quantum-inspired tensor network compression framework. We introduce two-dimensional infinite projected entangled pair states (iPEPS) — for the first time applied to LLM compression — to model the multi-directional quantum entanglement structure inherent in attention mechanisms and across Transformer layers, thereby revealing their intrinsic low-dimensional entanglement manifold. Leveraging tensor renormalization group (TRG) methods, we achieve polynomial-time efficient tensor contraction and identify redundant parameters via inter-layer entanglement analysis. Evaluated on LLaMA-2 7B, our method attains 93% memory reduction, 70% parameter pruning, and 50% and 25% speedups in training and inference, respectively, with only a 2–3% accuracy degradation. This establishes a novel paradigm for scalable, energy-efficient, quantum-aware AI architectures.

0 citationsRead paper

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

Jun 04, 2025

Traditional algebraic cryptosystems (e.g., RSA, ECC, lattice-based schemes) exhibit vulnerabilities under quantum attacks and structural cryptanalysis. Method: This paper proposes HFKR, a structure-free, quantum-resistant key generation scheme. It employs contraction-affine mappings over ℤ² to generate chaotic symbolic trajectories; characterizes their self-similarity and space-filling complexity via fractal dimension (empirically ≈1.06); and applies SHA3-512/SHAKE256 hashing for entropy amplification and chaotic parameter perturbation. Results: Under 250 perturbations, generated keys achieve a mean Hamming distance of 255, near-ideal bit-flip rates, and negligible entropy deviation; BLAKE3 underperforms due to insufficient diffusion. This work pioneers the rigorous integration of fractal geometry with cryptographic entropy modeling, establishing a lightweight, algebraically unstructured, and provably quantum-resistant paradigm.

0 citationsRead paper