Gartner Research

AI as a Target and Tool: An Attacker’s Perspective on ML

Summary

The use of AI in security has not gone unnoticed by attackers. Security and risk management technical professionals must understand how adversaries may attack security solutions based on ML at training and prediction stages, and how ML accelerates innovation in attacker methods.

Published: 19 June 2019

ID: G00381087

Analyst(s): Mario de Boer

Table Of Contents

Analysis

  • The Use of Machine Learning in Technical Security Controls
    • How Does ML Work?
    • ML Uses in Security
    • The Two Biggest Challenges in Applying ML to Security
  • Adversarial ML: Attacks on ML Techniques in Security Products
    • Data Poisoning Attacks at Training Time
    • Adversarial Inputs: Attacks at Runtime
  • Nefarious ML Use: Attacks Leveraging ML
    • Phishing
    • Identity Deception
    • Vulnerability Discovery and Exploitation
    • Malware
    • Others
    • ML Attacks on ML: Generative Adversarial Networks
  • Strengths
  • Weaknesses

Guidance

The Details

  • Resources to Experiment Yourself
    • Research
    • Datasets
    • ML Platforms
    • ML for Malware Detection
    • Adversarial Platforms

Gartner Recommended Reading

Already a Gartner client?

Become a Client

This research is reserved for paying clients. Speak with a Gartner specialist to learn how you can access this research as a client, plus insights, advice and tools to help you achieve your goals.

Contact Information

All fields are required.

By clicking the "Submit" button, you are agreeing to the Gartner Terms of Use and Privacy Policy.

©2021 Gartner, Inc. and/or its affiliates. All rights reserved. Gartner is a registered trademark of Gartner, Inc. and its affiliates. This publication may not be reproduced or distributed in any form without Gartner’s prior written permission. It consists of the opinions of Gartner’s research organization, which should not be construed as statements of fact. While the information contained in this publication has been obtained from sources believed to be reliable, Gartner disclaims all warranties as to the accuracy, completeness or adequacy of such information. Although Gartner research may address legal and financial issues, Gartner does not provide legal or investment advice and its research should not be construed or used as such. Your access and use of this publication are governed by Gartner’s Usage Policy. Gartner prides itself on its reputation for independence and objectivity. Its research is produced independently by its research organization without input or influence from any third party. For further information, see Guiding Principles on Independence and Objectivity.