On the Computational Entanglement of Distant Features in Adversarial Machine Learning

arXiv:2309.15669v4 Announce Type: replace
Abstract: Adversarial examples in machine learning has emerged as a focal point of research due to their remarkable ability to deceive models with seemingly inconspicuous input perturbations, potentially resulting in severe consequences. In this study, we undertake a thorough investigation into the emergence of adversarial examples, a phenomenon that can, in principle, manifest in a wide range of machine learning models. Through our research, we unveil a new notion termed computational entanglement, with its ability to …

abstract adversarial adversarial examples adversarial machine learning arxiv computational consequences cs.it cs.lg emergence entanglement examples features investigation machine machine learning math.it physics.comp-ph research study type