[FEEDBACK]: Integrate model skewing into data poisoning #109
robvanderveer
announced in
Machine Learning Security Topics
Replies: 2 comments 1 reply
-
|
I agree with you @robvanderveer but then there will be only 9 security risks associated with the OWASP ML page. How do we merge the overlapping contents associated with both the attacks i.e Model Skewing and Data Poisoning? |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
I absolutely agree with the merge. It was very hard to make a distinguish between the two. |
Beta Was this translation helpful? Give feedback.
-
|
How about we merge these two attacks and introduce Excessive Agency @robvanderveer as mentioned in #89? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Type
Suggestions for Improvement
What would you like to report?
[FEEDBACK]: Model skewing requires altering training data, making it a form of data poisoning. Therefore it is probably better to integrate the two threats.
Code of Conduct
Beta Was this translation helpful? Give feedback.
All reactions