MITRE and Microsoft update ATLAS with a generative AI focus
In one sentence MITRE and Microsoft add a generative AI focus to the ATLAS knowledge base: new tactics and techniques for LLM-based systems and case studies from 2023 incidents such as the ChatGPT plugin leak and PoisonGPT.
MITRE ATT&CK is the catalog security teams use to describe how attackers target IT systems. MITRE ATLAS does the same for artificial intelligence systems: it classifies known techniques for attacking, deceiving or manipulating AI models and collects real case studies.
On November 6, 2023 MITRE announced, together with Microsoft, an update dedicated to generative AI: new tactics and techniques derived from 2023 incidents involving LLM-based systems, new case studies and joint work on incident and vulnerability sharing.
Companies
MITRE, Microsoft
Tools
MITRE ATLAS
Tags
Sources
- https://www.mitre.org/news-insights/news-release/mitre-and-microsoft-collaborate-address-generative-ai-security-risks
- https://www.securityinfowatch.com/cybersecurity/press-release/53077388/mitre-and-microsoft-collaborate-to-address-generative-ai-security-risks
- https://www.helpnetsecurity.com/2023/11/06/mitre-microsoft-partnership/