VinayUPrabhu

↗ HN profile [ 19.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. LLMs Are Lexical Thijarians (vinayprabhu.substack.com)
  2. One thing I do when a new attack is published is to see if the 'jpeg' defense works. That is, will the jpeg compressed version of the adversarial image retain its adversarial threat? Turns out the attack from OpenAI…