# Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training Source: [Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:56:21.324Z Authors: Haichao Zhang, Jianyu Wang Published: 2019-07-24T22:43:55.000Z ## Abstract We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in generating attacks for training, which typically suffer from issues such as label leaking as noted in recent works. Differently, the proposed approach generates adversarial images for training through feature scattering in the latent space, which is unsupervised in nature and avoids label leaking. More importantly, this new approach generates perturbed images in a collaborative fashion, taking the inter-sample relationships into consideration. We conduct analysis on model robustness and demonstrate the effectiveness of the proposed approach through extensively experiments on different datasets compared with state-of-the-art approaches. ## 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. - [Adversarial Robustness on CIFAR-10 (L2, eps=8/255)](): Adversarial Robustness; CIFAR-10 L2, epsilon=8/255; Robust Acc (AA): 36.74. ## Original sources and implementation [Original paper]() [PDF]()