Improving behavior based authentication against adversarial attack using XAI

arXiv:2402.16430v1 Announce Type: new
Abstract: In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small changes learned by an adversarial attack model, when applied to the input, can cause significant changes in the output. Most research on adversarial attacks and corresponding defense methods focuses only on scenarios where adversarial samples are directly generated by the attack …

adversarial adversarial attack arxiv attack authentication classification cs.cr cs.hc domain input machine machine learning machine learning models manipulation networks neural networks security vulnerable xai