# NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

Source: [NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability](<https://www.sota2.com/research/paper/68fa7ad11e209131cea854d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:27:47.170Z

Authors: Krishna Kanth Nakka, Alexandre Alahi

Published: 2025-08-23T08:06:31.000Z

## Abstract

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this approach and introduce Neuron Attack for Transferability (NAT), a method designed to target specific neuron within the embedding. Our approach is motivated by the observation that previous layer-level optimizations often disproportionately focus on a few neurons representing similar concepts, leaving other neurons within the attacked layer minimally affected. NAT shifts the focus from embedding-level separation to a more fundamental, neuron-specific approach. We find that targeting individual neurons effectively disrupts the core units of the neural network, providing a common basis for transferability across different models. Through extensive experiments on 41 diverse ImageNet models and 9 fine-grained models, NAT achieves fooling rates that surpass existing baselines by over 14\\% in cross-model and 4\\% in cross-domain settings. Furthermore, by leveraging the complementary attacking capabilities of the trained generators, we achieve impressive fooling rates within just 10 queries. Our code is available at: https://krishnakanthnakka.github.io/NAT/

## 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](<https://arxiv.org/abs/2508.16937>)

[PDF](<https://arxiv.org/pdf/2508.16937.pdf>)
