Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks
Keywords:Machine Learning (ML), Computer Vision (CV)
AbstractWe propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: L0-bounded perturbations, adversarial patches, and adversarial frames. The L0-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for the challenging settings of 20x20 adversarial patches and 2-pixel wide adversarial frames for 224x224 images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. Our code is available at https://github.com/fra31/sparse-rs.
How to Cite
Croce, F., Andriushchenko, M., Singh, N. D., Flammarion, N., & Hein, M. (2022). Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6437-6445. https://doi.org/10.1609/aaai.v36i6.20595
AAAI Technical Track on Machine Learning I