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

TL;DR

This paper introduces a novel method combining SHAP analysis with an Optimal Epsilon technique to precisely craft adversarial examples, revealing vulnerabilities in machine learning models and emphasizing the need for ongoing security assessments.

Contribution

It presents a new approach that integrates feature importance analysis with an efficient epsilon search to improve evasion attack precision on ML models.

Findings

Effective identification of model vulnerabilities using SHAP

Precise generation of adversarial samples with minimal perturbation

Demonstrated applicability across diverse ML architectures

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 Epsilon technique, employing a Binary Search algorithm, efficiently determines the minimum epsilon needed for successful evasion. Evaluation across diverse machine learning architectures demonstrates the technique's precision in generating adversarial samples, underscoring its efficacy in manipulating model outcomes. This study emphasizes the critical importance of continuous assessment and monitoring to identify and mitigate potential security risks in machine learning systems.