Nicholas Carlini - Some Lessons from Adversarial Machine Learning

Поділитися
Вставка
  • Опубліковано 14 гру 2024

КОМЕНТАРІ • 1

  • @juliesteele5021
    @juliesteele5021 2 місяці тому +32

    Nice talk! I disagree that adversarial robustness has only one attack and differs from other computer security in that way.
    Once the simple PGD attack is solved in a tight epsilon ball, you still can’t say there is no adversarial image that breaks the model. Enumerating all possible attacks is still very difficult/ impossible for now.