Search
Find a vulnerability
Search criteria
ⓘ
Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.
1 vulnerability by New Microsoft AI Product
AVID-2023-V011
Vulnerability from avid – Published: 2023-03-31 – Updated: 2023-03-31 ATLAS Case StudySummary
The Azure Red Team performed a red team exercise on a new Microsoft product designed for running AI workloads at the edge. This exercise was meant to use a automated system to continuously manipulate a target image to cause the ML model to produce misclassifications.
Risk domain
Security
SEP view
S0301: Information Leak, S0403: Adversarial Example
Lifecycle
L06: Deployment
Organisations
New Microsoft AI Product (deployer)
Affected artifacts
1 artifact
| Artifact | Type |
|---|---|
| New Microsoft AI Product | System |
References
1 reference
| URL | Label |
|---|---|
| https://atlas.mitre.org/studies/AML.CS0011 | Microsoft Edge AI Evasion |