Two Six works with partners to protect machine learning systems

Two Six Labs is pleased to announce our work to protect machine learning systems with Microsoft, MITRE, Bosch, IBM, NVIDIA, Airbus, Deep Instinct, the University of Toronto, Cardiff University, Software Engineering Institute/Carnegie Mellon University, PricewaterhouseCoopers, and Berryville Institute of Machine Learning.

This collaborative effort has produced a publicly available codebase to aid security analysts in defending against new and upcoming threats to ML systems.

Github repo:

https://github.com/mitre/advmlthreatmatrix

Further reading:

https://insights.sei.cmu.edu/cert/2020/10/adversarial-ml-threat-matrix-adversarial-tactics-techniques-and-common-knowledge-of-machine-learning.html

https://www.mitre.org/publications/project-stories/mitre-microsoft-others-take-on-machine-learning-threats

https://www.microsoft.com/security/blog/2020/10/22/cyberattacks-against-machine-learning-systems-are-more-common-than-you-think/

https://www.darkreading.com/vulnerabilities—threats/advanced-threats/microsoft-and-others-catalog-threats-to-machine-learning-systems/d/d-id/1339354