Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems
Hikmat Karimov, Rahid Zahid Alekberli
Why It Matters
What makes this one worth your time
This work offers a potentially rigorous approach to AI safety by grounding ethical violations in physical and informational principles, which could lead to more reliable autonomous systems.
A novel framework linking thermodynamics and stochastic control for AI safety and stability.
Summary
The paper introduces the Kerimov-Alekberli model, an information-geometric framework that connects non-equilibrium thermodynamics with stochastic control to address AI safety and system stability. It uses the Kullback-Leibler divergence and Fisher Information Metric to detect systemic anomalies and validates the model on datasets like NSL-KDD and UAV simulations.
Key contributions
- Introduction of the Kerimov-Alekberli model for AI safety.
- Establishing a formal isomorphism between non-equilibrium thermodynamics and stochastic control.
- Validation of the model on NSL-KDD dataset and UAV simulations.
Notable insights
- Linking non-equilibrium thermodynamics with stochastic control to redefine AI safety.
- Using the Fisher Information Metric to dynamically govern the Kullback-Leibler divergence threshold.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2604.24083v2 Announce Type: replace Abstract: Runtime monitoring of stochastic systems must distinguish nominal distributional relaxation from regime departure while controlling repeated-test false alarms under explicit validity assumptions. This paper links relative-entropy dissipation, information geometry, and sequential inference in a bounded first-passage monitoring architecture. For reversible Fokker--Planck dynamics, relative entropy to an invariant density is non-increasing; under exogenous forcing, its derivative decomposes into nominal dissipation and an information-space forcing term. The runtime layer uses Gaussian window surrogates, nominal-relative covariance shrinkage, a coordinate-consistent relative precision diagnostic, and randomized conformal ranks aggregated by a mixture power-martingale process. Analytical Ornstein--Uhlenbeck validation gives zero positive nominal Kullback--Leibler increments, forcing-identity residuals below 3.31 x 10^-6, and coordinate-invariance errors at numerical roundoff. On NSL-KDD, the monitor yields 0/100 alarms on internal nominal streams but 63/100 on official test-normal streams; post-change detection is 99.0% for seen and 98.53% for test-only attack types with median one-window delay. On UNSW-NB15, internal-null alarms are 0/100, whereas official test-normal alarms rise to 90/100; post-change detection is 81.33%, with 18.67% pre-change alarms. In these evaluations, calibration transport emerges as a major deployment constraint. No universal benchmark superiority, causal inference, or physical-work interpretation is claimed.