MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception

arXiv:2404.15656v1 Announce Type: new
Abstract: Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing erroneous predictions. To address this, we propose a methodology combining SHapley Additive exPlanations (SHAP) for feature importance analysis with an innovative Optimal Epsilon technique for conducting evasion attacks. Our approach begins with SHAP-based analysis to understand model vulnerabilities, crucial for devising targeted evasion strategies. The Optimal …

abstract adversarial adversarial attacks arxiv attacks concerns cs.cr cs.lg data deception epsilon evasion features importance machine machine learning methodology predictions raise reliability type vulnerabilities