# MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps Source: [MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:12:28.025Z Authors: Muhammad Awais, Fengwei Zhou, Chuanlong Xie, Jiawei Li, Sung-Ho Bae, Zhenguo Li Published: 2021-11-09T12:03:20.000Z ## Abstract Deep neural networks are susceptible to adversarially crafted, small and imperceptible changes in the natural inputs. The most effective defense mechanism against these examples is adversarial training which constructs adversarial examples during training by iterative maximization of loss. The model is then trained to minimize the loss on these constructed examples. This min-max optimization requires more data, larger capacity models, and additional computing resources. It also degrades the standard generalization performance of a model. Can we achieve robustness more efficiently? In this work, we explore this question from the perspective of knowledge transfer. First, we theoretically show the transferability of robustness from an adversarially trained teacher model to a student model with the help of mixup augmentation. Second, we propose a novel robustness transfer method called Mixup-Based Activated Channel Maps (MixACM) Transfer. MixACM transfers robustness from a robust teacher to a student by matching activated channel maps generated without expensive adversarial perturbations. Finally, extensive experiments on multiple datasets and different learning scenarios show our method can transfer robustness while also improving generalization on natural images. ## 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. - [Image Classification on CIFAR-10 (test) (Adversarial Robustness - PGD 100 & Auto Attack)](): Image Classification; CIFAR-10 (test); Clean Accuracy: 91.17. - [Adversarial Image Classification on ImageNet (Linf eps=4/255, test)](): Image Classification; ImageNet Linf epsilon=4/255 (test); Accuracy: 62.05. - [Adversarial Robustness Accuracy on CIFAR-100 (test) (FGSM and PGD Steps)](): Image Classification; CIFAR-100 (test); Clean Accuracy: 68.91. - [Image Classification on ImageNet Linf epsilon=2/255 (test)](): Image Classification; ImageNet Linf epsilon=2/255 (test); Accuracy (Clean): 62.05. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()