#sercurityresearch — Public Fediverse posts on home.social

With all of AI’s potential to empower people and organizations, it also comes with risks that the security community must address.

we’re sharing some recent developments so that the community can be better informed and better equipped for a new world of AI exploration:

- New research: A dedicated AI Security Red Team within Microsoft Threat Intelligence explored how traditional software threats affect AI and how security professionals, developers, and machine learning engineers should think about securing and monitoring AI and machine learning models.

- New tools for defenders: Microsoft recently released an open-source automation tool for security testing of AI systems called Counterfit (https://github.com/Azure/counterfit/ ).

- Industry collaboration to help secure the AI supply chain: We worked with Hugging Face, one of the most popular machine learning model repositories, to mitigate threats to AI and machine learning frameworks by collaborating on an AI-specific security scanner.

Find out what microsoft AI Security Red Team investigated:

https://www.microsoft.com/en-us/security/blog/2023/03/02/new-research-tooling-and-partnerships-for-more-secure-ai-and-machine-learning/

MITRE ATLAS, the ATT&CK-style framework for adversarial machine learning: https://atlas.mitre.org/

#security #ai #Counterfit #azure #microsoft #redteam #airedteam #research #sercurityresearch #AIsecurity #ML #threatintelligence #openai #mitre #mitreatlas #atlas #python #caldera #threatmodeling #threat #cybersecurity #cloud #cloudsecurity