Topological approach detects adversarial attacks in multimodal AI systems

by AI Generated Robotic ContentAI/ML NewsPosted on Comments are Disabled

New vulnerabilities have emerged with the rapid advancement and adoption of multimodal foundational AI models, significantly expanding the potential for cybersecurity attacks. Researchers at Los Alamos National Laboratory have put forward a novel framework that identifies adversarial threats to foundation models—artificial intelligence approaches that seamlessly integrate and process text and image data. This work empowers …

Read more “Topological approach detects adversarial attacks in multimodal AI systems”

A thermodynamic approach to machine learning: How optimal transport theory can improve generative models

by AI Generated Robotic ContentAI/ML NewsPosted on Comments are Disabled

Joint research led by Sosuke Ito of the University of Tokyo has shown that nonequilibrium thermodynamics, a branch of physics that deals with constantly changing systems, explains why optimal transport theory, a mathematical framework for the optimal change of distribution to reduce cost, makes generative models optimal. As nonequilibrium thermodynamics has yet to be fully …

Read more “A thermodynamic approach to machine learning: How optimal transport theory can improve generative models”