I gave a keynote at zeronights about ML/AI and security. Slides are here: https://docs.google.com/presentation/d/16BWLRm4aNdxToJO-_63s1gLlw-hbSXlQE-jSzzsHkIw/edit?usp=sharing … - Lots of opinions to disagree with.
-
Show this thread
-
Some clarification: I am not saying "ML for defense does not work". I am saying that focus on problems where your problem distribution does not change (or changes slowly) is more promising.
6 replies 1 retweet 16 likesShow this thread
Replying to @halvarflake
How about using ML to learn typical user behaviour, and identify sudden changes? My users tend to change much slower than my attackers.
0 replies
1 retweet
4 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.