
AttackBench is a unified framework that enables a fair and comprehensive evaluation of gradient-based adversarial attacks against machine learning models. It provides a categorization of existing attacks, introduces a novel optimality metric to rank their performance, and highlights implementation issues that prevent many attacks from finding better solutions.


coremsg

comprehensive-evaluation-of-gradient-based-adversarial-attacks-attackbench-framework


Comprehensive Evaluation of Gradient-based Adversarial Attacks: AttackBench Framework


title_rewrite


A novel methodology that combines SHAP-based feature importance analysis with an optimal epsilon technique to generate highly effective and precise adversarial samples that can evade machine learning models.


manipulating-feature-importance-to-generate-effective-evasion-attacks-on-machine-learning-models


Manipulating Feature Importance to Generate Effective Evasion Attacks on Machine Learning Models
