Microsoft releases an open framework to detect threats against ML systems

Machine learning (ML) is now used in various industries including finance, healthcare, and defense. Since the attacks on commercial ML systems are increasing, security of ML systems is really important. In fact, in the last three years, major companies such as Google, Amazon, Microsoft, and Tesla, have had their ML systems tricked, evaded, or misled. To empower security analysts to detect, respond to, and remediate threats against ML systems, Microsoft along with MITRE, and contributions from 11 organizations including IBM, NVIDIA, Bosch, have released the Adversarial ML Threat Matrix, an industry-focused open framework for security analysts.

This threat matrix came out of partnership with 12 industry and academic research groups with the goal of empowering security analysts to orient themselves to these new and upcoming threats. The framework is seeded with a curated set of vulnerabilities and adversary behaviors that Microsoft and MITRE have vetted to be effective against production ML systems. This framework used ATT&CK as a template since security analysts are already familiar with using this type of matrix.

You can check out the Adversarial ML Threat Matrix here.

Source: Microsoft