Eigenpatches - Adversarial Patches from Principal Components

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 computationally expensiveness by analyzing 375 generated patches, calculating the principal components of these and shows, that traversing the spanned up subspace of the resulting “eigenpatches” can be used to create patches that can be used to fool the attacked YOLOv7 object detector successfully. Furthermore, the influence regarding the mean average precision of the number of principal components used for the patch recreation and the sampling size for the principal component analysis are investigated. Patches generated this way can either be used as a starting point for further optimization or as an adversarial patch as it is.