Microsoft Azure Service Disruption

Summary

The Microsoft AI Red Team performed a red team exercise on an internal Azure service with the intention of disrupting its service. This operation had a combination of traditional ATT&CK enterprise techniques such as finding valid account, and exfiltrating data -- all interleaved with adversarial ML specific steps such as offline and online evasion examples. Target: Internal Microsoft Azure Service Actor: Microsoft AI Red Team Procedure: 1. The team first performed reconnaissance to gather information about the target ML model. 2. The team used a valid account to gain access to the network. 3. The team found the model file of the target ML model and the necessary training data. 4. The team exfiltrated the model and data via traditional means. 5. Using the target model and data, the red team crafted evasive adversarial data in an offline manor. 6. The team used an exposed API to access the target model. 7. The team submitted the adversarial examples to the API to verify their efficacy on the production system. 8. The team performed an online evasion attack by replaying the adversarial examples and accomplished their goals.

Deployers

• Internal Microsoft Azure Service

Tags

• MITRE ATLAS
• AML.CS0010