# Stochastic sparse adversarial attacks Source: [Stochastic sparse adversarial attacks]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:57:05.246Z Authors: Manon C\\'esaire, Lucas Schott, Hatem Hajri, Sylvain Lamprier, Patrick Gallinari Published: 2020-11-24T22:07:51.000Z ## Abstract This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (NNC). SSAA offer new examples of sparse (or $L\_0$) attacks for which only few methods have been proposed previously. These attacks are devised by exploiting a small-time expansion idea widely used for Markov processes. Experiments on small and large datasets (CIFAR-10 and ImageNet) illustrate several advantages of SSAA in comparison with the-state-of-the-art methods. For instance, in the untargeted case, our method called Voting Folded Gaussian Attack (VFGA) scales efficiently to ImageNet and achieves a significantly lower $L\_0$ score than SparseFool (up to $\\frac{2}{5}$) while being faster. Moreover, VFGA achieves better $L\_0$ scores on ImageNet than Sparse-RS when both attacks are fully successful on a large number of samples. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()