OWASP / www-project-machine-learning-security-top-10

OWASP Machine Learning Security Top 10 Project
http://owasp.org/www-project-machine-learning-security-top-10/
Other
76 stars 25 forks source link

[FEEDBACK]: Rename adversarial attack to something less ambiguous #84

Closed robvanderveer closed 1 year ago

robvanderveer commented 1 year ago

Type

Suggestions for Improvement

What would you like to report?

The term adversarial attack usually has a broader definition than the intention of ML01. For example it usually includes data poisoning. The intention seems to refer to what is more often called 'evasion attack'. The problem with that term is that it usually means small changes to the input. This is why in the AI guide we used the term 'input manipulation', which is more clear.

Code of Conduct

aryanxk02 commented 1 year ago

Shall I take up this issue @robvanderveer? I'll replace the term adverarial with input manipulation wherever necessary.

shsingh commented 1 year ago

sure @aryanxk02 ... thank you!

shsingh commented 1 year ago

created #106 for you to work on @aryanxk02