analiza aiqbench
This research proposes an entropy-optimizing framework to enhance AI resilience and robustness against adversarial attacks by deriving mathematically sound conditions for global optimality. The approach introduces self-attacking learning algorithms that generate optimal training data, enabling the development of significantly simpler and cheaper models with superior predictive performance across diverse domains like hydrodynamics and biomedicine. By reducing reliance on massive datasets while outperforming standard deep learning architectures, this work offers a novel pathway for energy-efficient and reliable AI deployment.
Entropic perspective on AI resilience, data-minimal learning and optimal control
arXiv:2310.14421v5 Announce Type: replace-cross Abstract: Behind the general terms like adversarial attacks and generative adversarial networks (GANs), such criteria as AI resilience and AI robustness gained a crucial importance, in trying to make the emergent AI tools reliable, energy-efficient and safe. From mathematical perspective, these problems boil down to finding a mathematically-sound quantification of the smallest-sufficient amounts of the perturbations of function arguments that lead to the largest possible perturbations of the approximated function values. Here, the entropy-optimising perspective on adversarial algorithms from Artificial Intelligence (AI) is proposed to attack this problem. It is shown that adopting this perspective helps proving computational conditions for the global optimality and uniqueness of adversarial attacks based on cheaply-verifiable mathematical criteria. Further, it is shown how this perspective can be used for developing self-attacking learning algorithms, that generate optimal new data points for training, replacing one of the trained agents with this mathematical criterium. On a broad selection of various synthetic and real-life problems from hydrodynamics and biomedicine, it is shown that such self-attacking learning algorithms allow training orders-of-magnitude simpler and cheaper models with superior performance - and can be used to directly train the optimal controls in complex systems, requiring only a small fraction of the training data and outperforming the as-comprehensive-as-the-author-was-able-to-find set of contemporary AI tools (like boosted Random Forests, deep neural networks, foundational models based on transformer architectures, etc.) in complexity (measured as the model descriptor length) and predictive performance.}
Abstract:Behind the general terms like adversarial attacks and generative adversarial networks (GANs), such criteria as AI resilience and AI robustness gained a crucial importance, in trying to make the emergent AI tools reliable, energy-efficient and safe. From mathematical perspective, these problems boil down to finding a mathematically-sound quantification of the smallest-sufficient amounts of the perturbations of function arguments that lead to the largest possible perturbations of the approximated function values. Here, the entropy-optimising perspective on adversarial algorithms from Artificial Intelligence (AI) is proposed to attack this problem. It is shown that adopting this perspective helps proving computational conditions for the global optimality and uniqueness of adversarial attacks based on cheaply-verifiable mathematical criteria. Further, it is shown how this perspective can be used for developing self-attacking learning algorithms, that generate optimal new data points for training, replacing one of the trained agents with this mathematical criterium. On a broad selection of various synthetic and real-life problems from hydrodynamics and biomedicine, it is shown that such self-attacking learning algorithms allow training orders-of-magnitude simpler and cheaper models with superior performance - and can be used to directly train the optimal controls in complex systems, requiring only a small fraction of the training data and outperforming the as-comprehensive-as-the-author-was-able-to-find set of contemporary AI tools (like boosted Random Forests, deep neural networks, foundational models based on transformer architectures, etc.) in complexity (measured as the model descriptor length) and predictive performance.}
Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2310.14421 [stat.ML]
(or arXiv:2310.14421v5 [stat.ML] for this version)
From: Illia Horenko Dr. [view email] [v1] Thu, 19 Oct 2023 10:36:02 UTC (4,342 KB) [v2] Mon, 6 Nov 2023 15:57:27 UTC (4,348 KB) [v3] Tue, 14 Nov 2023 18:13:13 UTC (4,449 KB) [v4] Wed, 15 Nov 2023 11:05:34 UTC (4,449 KB) [v5] Tue, 20 Oct 2026 11:25:18 UTC (5,919 KB)
Text integral sub licența deschisă a publicației · 302 cuvinte