MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
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
Code (1)
Similar Papers 제목 키워드 기반
AI capabilities can be significantly improved without expensive retraining
State-of-the-art AI systems can be significantly improved without expensive retraining via "post-training enhancements"-techniques applied after initial training like fine-tuning the system to use a web browser. We revie…
Robust Audio-Visual Speech Enhancement: Correcting Misassignments in Complex Environments with Advanced Post-Processing
This paper addresses the prevalent issue of incorrect speech output in audio-visual speech enhancement (AVSE) systems, which is often caused by poor video quality and mismatched training and test data. We introduce a pos…
Speech EnhancementPosterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise…
Speech EnhancementPost-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields
Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns about their real-world applicability. Wh…
Graph Representation LearningNode ClassificationRelational ReasoningRepresentation LearningNORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Vision--language--action (VLA) models have recently shown promising performance on a variety of embodied tasks, yet they still fall short in reliability and generalization, especially when deployed across different embod…