Efficient Hit-Spectrum-Guided Fast Gradient Sign Method: An Adjustable Approach with Memory and Runtime Optimizations

Daniel Rashedi, Sibylle Schupp

2025

Abstract

Fast Gradient Sign Method (FGSM) is an effective method for generating adversarial inputs for neural networks, but it is memory-intensive. DeepFault reduces the memory costs of FGSM by transferring Spectrum-Based Fault Localization to neural networks. SBFL is a technique traditionally using the execution trace of a program to identify suspicious code locations that are likely to contain faults. DeepFault employs SBFL to identify neurons in a neural network that are likely to be responsible for misclassifications to guide FGSM. We propose an adjustable hit-spectrum-guided FGSM approach applying a sub-model strategy to avoid gradient ascent evaluation over the entire model. Additionally, we alter DeepFault’s hit-spectrum computation to be vector-based to allow parallelization of computation, and we modify the hit spectrum to depend on a specific class to allow targeted adversarial input generation. We conduct an experimental evaluation on image classification models showing how our approach allows trading off effectiveness of adversarial input generation with reduced runtimes while maintaining scalability regarding larger models, with maximum runtimes on the order of tens of seconds. For larger sample sizes, our approach reduces runtimes to fractions of 1/300 and less compared to DeepFault. When processing larger models, it requires only one-third of FGSM’s memory usage.

Paper Citation

in Harvard Style

Rashedi D. and Schupp S. (2025). Efficient Hit-Spectrum-Guided Fast Gradient Sign Method: An Adjustable Approach with Memory and Runtime Optimizations. In Proceedings of the 20th International Conference on Software Technologies - Volume 1: ICSOFT; ISBN 978-989-758-757-3, SciTePress, pages 51-62. DOI: 10.5220/0013463100003964

in Bibtex Style

@conference{icsoft25,
author={Daniel Rashedi and Sibylle Schupp},
title={Efficient Hit-Spectrum-Guided Fast Gradient Sign Method: An Adjustable Approach with Memory and Runtime Optimizations},
booktitle={Proceedings of the 20th International Conference on Software Technologies - Volume 1: ICSOFT},
year={2025},
pages={51-62},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013463100003964},
isbn={978-989-758-757-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Software Technologies - Volume 1: ICSOFT
TI - Efficient Hit-Spectrum-Guided Fast Gradient Sign Method: An Adjustable Approach with Memory and Runtime Optimizations
SN - 978-989-758-757-3
AU - Rashedi D.
AU - Schupp S.
PY - 2025
SP - 51
EP - 62
DO - 10.5220/0013463100003964
PB - SciTePress