Supporting AI/ML Security Workers through an Adversarial Techniques, Tools, and Common Knowledge (AI/ML ATT&CK) Framework

TL;DR

This paper introduces the AI/ML ATT&CK framework, a comprehensive tool designed to assist AI/ML security professionals in understanding and applying offensive and defensive tactics for secure AI system development.

Contribution

The paper presents a novel framework that consolidates adversarial techniques, tools, and knowledge to support AI/ML security workers in their tasks.

Findings

Framework enables intuitive exploration of offensive and defensive tactics

Supports security workers in developing more secure AI/ML systems

Facilitates knowledge sharing among AI/ML security professionals

Abstract

This paper focuses on supporting AI/ML Security Workers -- professionals involved in the development and deployment of secure AI-enabled software systems. It presents AI/ML Adversarial Techniques, Tools, and Common Knowledge (AI/ML ATT&CK) framework to enable AI/ML Security Workers intuitively to explore offensive and defensive tactics.