Eigenpatches – Adversarial Patches from Principal Components

06/19/2023
by   Jens Bayer, et al.
0

Adversarial patches are still a simple yet powerful white box attack that can be used to fool object detectors by suppressing possible detections. The patches of these so-called evasion attacks are computational expensive to produce and require full access to the attacked detector. This paper addresses the problem of computational expensiveness by analyzing 375 generated patches, calculating the principal components of these and show, that linear combinations of the resulting "eigenpatches" can be used to fool object detections successfully.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset