Search papers, labs, and topics across Lattice.
The paper introduces the Kerimov-Alekberli model, an information-geometric framework that links non-equilibrium thermodynamics to stochastic control for AI safety. It defines systemic anomalies as deviations from a Riemannian manifold, using Kullback-Leibler divergence and a dynamic threshold derived from the Fisher Information Metric. Validated on NSL-KDD and UAV trajectory simulations, the model demonstrates effective real-time anomaly detection, grounding ethical violations in quantifiable physical work and entropic information.
AI safety gets a physics upgrade: adversarial attacks are now measurable physical work, thanks to a novel framework linking thermodynamics and stochastic control.
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.
