The Kerimov-Alekberli Model: An Information-Geometric Framework for Real-Time System Stability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karimov, Hikmat, Alekberli, Rahid Zahid
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917461989785600
author Karimov, Hikmat
Alekberli, Rahid Zahid
author_facet Karimov, Hikmat
Alekberli, Rahid Zahid
contents This study introduces the Kerimov-Alekberli model, a novel information-geometric framework that redefines AI safety by formally linking non-equilibrium thermodynamics to stochastic control for the ethical alignment of autonomous systems. By establishing a formal isomorphism between non-equilibrium thermodynamics and stochastic control, we define systemic anomalies as deviations from a Riemannian manifold. The model utilizes the Kullback-Leibler divergence as the primary metric, governed by a dynamic threshold derived from the Fisher Information Metric. We further ground this framework in the Landauer Principle, proving that adversarial perturbations perform measurable physical work by increasing the system's informational entropy. Validation on the NSL-KDD dataset and unmanned aerial vehicle trajectory simulations demonstrated that our model achieves effective real-time detection via the FPT trigger, with strong performance metrics (e.g., high accuracy and low FPR) on benchmark datasets. This study provides a rigorous physical foundation for AI safety, transitioning from heuristic, rule-based ethical frameworks to a thermodynamics-based stability paradigm by grounding ethical violations in quantifiable physical work and entropic information.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24083
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Kerimov-Alekberli Model: An Information-Geometric Framework for Real-Time System Stability
Karimov, Hikmat
Alekberli, Rahid Zahid
Artificial Intelligence
Computation and Language
Cryptography and Security
Machine Learning
This study introduces the Kerimov-Alekberli model, a novel information-geometric framework that redefines AI safety by formally linking non-equilibrium thermodynamics to stochastic control for the ethical alignment of autonomous systems. By establishing a formal isomorphism between non-equilibrium thermodynamics and stochastic control, we define systemic anomalies as deviations from a Riemannian manifold. The model utilizes the Kullback-Leibler divergence as the primary metric, governed by a dynamic threshold derived from the Fisher Information Metric. We further ground this framework in the Landauer Principle, proving that adversarial perturbations perform measurable physical work by increasing the system's informational entropy. Validation on the NSL-KDD dataset and unmanned aerial vehicle trajectory simulations demonstrated that our model achieves effective real-time detection via the FPT trigger, with strong performance metrics (e.g., high accuracy and low FPR) on benchmark datasets. This study provides a rigorous physical foundation for AI safety, transitioning from heuristic, rule-based ethical frameworks to a thermodynamics-based stability paradigm by grounding ethical violations in quantifiable physical work and entropic information.
title The Kerimov-Alekberli Model: An Information-Geometric Framework for Real-Time System Stability
topic Artificial Intelligence
Computation and Language
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2604.24083