A Novel Approach to Guard from Adversarial Attacks using Stable Diffusion

arXiv:2405.01838v1 Announce Type: new
Abstract: Recent developments in adversarial machine learning have highlighted the importance of building robust AI systems to protect against increasingly sophisticated attacks. While frameworks like AI Guardian are designed to defend against these threats, they often rely on assumptions that can limit their effectiveness. For example, they may assume attacks only come from one direction or include adversarial images in their training data. Our proposal suggests a different approach to the AI Guardian framework. Instead of …

abstract adversarial adversarial attacks adversarial machine learning ai systems arxiv assumptions attacks building cs.lg diffusion frameworks importance machine machine learning novel protect robust stable diffusion systems threats type while