SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge

arXiv:2402.14937v1 Announce Type: new
Abstract: Adversarial examples are malicious inputs to machine learning models that trigger a misclassification. This type of attack has been studied for close to a decade, and we find that there is a lack of study and formalization of adversary knowledge when mounting attacks. This has yielded a complex space of attack research with hard-to-compare threat models and attacks. We focus on the image classification domain and provide a theoretical framework to study adversary knowledge inspired …

abstract adversarial adversarial examples arxiv attacks cs.cr cs.lg examples framework inputs knowledge machine machine learning machine learning models study type