# MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification Source: [MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:53:16.434Z Authors: Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr Published: 2024-06-09T22:14:55.000Z ## Abstract We present a simple yet effective method to improve the robustness of both Convolutional and attention-based Neural Networks against adversarial examples by post-processing an adversarially trained model. Our technique, MeanSparse, cascades the activation functions of a trained model with novel operators that sparsify mean-centered feature vectors. This is equivalent to reducing feature variations around the mean, and we show that such reduced variations merely affect the model's utility, yet they strongly attenuate the adversarial perturbations and decrease the attacker's success rate. Our experiments show that, when applied to the top models in the RobustBench leaderboard, MeanSparse achieves a new robustness record of 75.28% (from 73.71%), 44.78% (from 42.67%) and 62.12% (from 59.56%) on CIFAR-10, CIFAR-100 and ImageNet, respectively, in terms of AutoAttack accuracy. Code is available at https://github.com/SPIN-UMass/MeanSparse ## 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 ImageNet (Standard and Robust Accuracy)](): Image Classification; ImageNet; Standard Accuracy: 77.96. - [Image Classification on ImageNet 1k (test) (Robustness Metrics)](): Image Classification; ImageNet 1k (test); Clean Accuracy: 77.96. ## Original sources and implementation [Original paper]() [PDF]()