Adversarial Threat Landscape for AI Systems
Find a file
2022-07-25 16:12:26 -04:00
_nuxt c3803ff 2022-03-31 22:09:30 +00:00
atlas-data@522e5f4502 c3803ff 2022-03-31 22:09:30 +00:00
content c3803ff 2022-03-31 22:09:30 +00:00
matrix c3803ff 2022-03-31 22:09:30 +00:00
navigator c3803ff 2022-03-31 22:09:30 +00:00
resources c3803ff 2022-03-31 22:09:30 +00:00
studies c3803ff 2022-03-31 22:09:30 +00:00
tactics c3803ff 2022-03-31 22:09:30 +00:00
techniques c3803ff 2022-03-31 22:09:30 +00:00
.gitmodules c3803ff 2022-03-31 22:09:30 +00:00
.nojekyll c3803ff 2022-03-31 22:09:30 +00:00
404.html c3803ff 2022-03-31 22:09:30 +00:00
CHANGELOG.md c3803ff 2022-03-31 22:09:30 +00:00
favicon.ico c3803ff 2022-03-31 22:09:30 +00:00
index.html c3803ff 2022-03-31 22:09:30 +00:00
LICENSE.txt c3803ff 2022-03-31 22:09:30 +00:00
README.md c3803ff 2022-03-31 22:09:30 +00:00

ATLAS

MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems), is a knowledge base of adversary tactics, techniques, and case studies for machine learning (ML) systems based on real-world observations, demonstrations from ML red teams and security groups, and the state of the possible from academic research.

ATLAS is modeled after the MITRE ATT&CK® framework and its tactics and techniques are complementary to those in ATT&CK. Machine learning is increasingly used across a variety of industries and there are a growing number of vulnerabilities. We developed ATLAS to raise awareness of these threats and present them in a way familiar to security researchers.

Visit the ATLAS website at https://atlas.mitre.org!