Git-Mirrors/advmlthreatmatrix
1
0
Fork 0
mirror of https://github.com/mitre/advmlthreatmatrix.git synced 2025-12-01 03:26:52 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update adversarial-ml-threat-matrix.md

Browse source
This commit is contained in:
ramtherunner 2020-10-15 23:47:00 -07:00 • committed by GitHub
parent 777d6796da
commit 0841f59983
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
pages/adversarial-ml-threat-matrix.md
View file

@ -20,7 +20,7 @@ However, there are two main differences:
## Things to keep in mind before you use the framework:
1. This is a **first cut attempt** at collating known adversary techniques against ML Systems. We plan to iterate on the framework based on feedback from the security and adversarial machine learning community (please engage with us and help make the matrix better!). Net-Net: This is a *living document* that will be routinely updated.
- Have feedback or improvements? We want in! See [Feedback](/pages/readme#feedback-and-getting-involved)
- Have feedback or improvements? We want in! See [Feedback](/pages/readme.md#feedback-and-getting-involved)
2. Only known bad is listed in the Matrix. Adversarial ML is an active area of research with new classes constantly being discovered. If you find a technique that is not listed, please enlist it in the framework (see section on Feedback)
3. We are not prescribing definitive defenses at this point - The world of adversarial. We are already in conversations to add best practices in future revisions such as adversarial training for adversarial examples, restricting the number of significant digits in confidence score for model stealing.
4. This is not a risk prioritization framework - The Threat Matrix only collates the known techniques; it does not provide a means to prioritize the risks.