# Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition

Source: [Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition](<https://www.sota2.com/research/paper/68fa79ec1e209131cea7ff94>)

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

Data updated: 2026-07-04T05:01:04.041Z

Authors: R\\'ois\\'in Luo, James McDermott, Colm O'Riordan

Published: 2024-08-02T09:35:06.000Z

## Abstract

Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial attacks. Understanding the mechanisms of perturbation robustness is critical for global interpretability. We present a model-agnostic, global mechanistic interpretability method to interpret the perturbation robustness of image models. This research is motivated by two key aspects. First, previous global interpretability works, in tandem with robustness benchmarks, e.g. mean corruption error (mCE), are not designed to directly interpret the mechanisms of perturbation robustness within image models. Second, we notice that the spectral signal-to-noise ratios (SNR) of perturbed natural images exponentially decay over the frequency. This power-law-like decay implies that: Low-frequency signals are generally more robust than high-frequency signals -- yet high classification accuracy can not be achieved by low-frequency signals alone. By applying Shapley value theory, our method axiomatically quantifies the predictive powers of robust features and non-robust features within an information theory framework. Our method, dubbed as \\textbf{I-ASIDE} (\\textbf{I}mage \\textbf{A}xiomatic \\textbf{S}pectral \\textbf{I}mportance \\textbf{D}ecomposition \\textbf{E}xplanation), provides a unique insight into model robustness mechanisms. We conduct extensive experiments over a variety of vision models pre-trained on ImageNet to show that \\textbf{I-ASIDE} can not only \\textbf{measure} the perturbation robustness but also \\textbf{provide interpretations} of its mechanisms.

## 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/2408.01139>)

[PDF](<https://arxiv.org/pdf/2408.01139.pdf>)
