# Interpretability-Guided Test-Time Adversarial Defense

Source: [Interpretability-Guided Test-Time Adversarial Defense](<https://www.sota2.com/research/paper/68fa74e31e209131cea6471e>)

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

Data updated: 2025-10-28T13:57:09.598Z

Authors: Akshay Kulkarni, Tsui-Wei Weng

Published: 2024-09-23T16:40:10.000Z

## Abstract

We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can significantly improve the robustness-accuracy tradeoff while incurring minimal computational overhead. While being among the most efficient test-time defenses (4x faster), our method is also robust to a wide range of black-box, white-box, and adaptive attacks that break previous test-time defenses. We demonstrate the efficacy of our method for CIFAR10, CIFAR100, and ImageNet-1k on the standard RobustBench benchmark (with average gains of 2.6%, 4.9%, and 2.8% respectively). We also show improvements (average 1.5%) over the state-of-the-art test-time defenses even under strong adaptive attacks.

## 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/2409.15190>)

[PDF](<https://arxiv.org/pdf/2409.15190.pdf>)