Efficient adversarial generation through selective SBFL guidance and automated sub-model strategy
Publikationstyp
Conference Paper
Date Issued
2025-06
Sprache
English
First published in
Number in series
3144
Start Page
3
End Page
32
Citation
20th International Conference on Software Technologies, ICSOFT 2025 (2026)
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
Springer
ISBN of container
978-3-0323-7353-3
978-3-0323-7352-6
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 (SBFL) to neural networks. SBFL is a technique traditionally using the execution trace of a program to iden-tify 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 SBFL-guided adversarial input generation approach that addresses both memory and runtime efficiency challenges for sequential classification models. Our contributions include: (1) an automated and adjustable sub-model strategy that selects smaller model configurations for input synthesis, reducing both memory overhead and computational effort, (2) vector-based hit-spectrum computation using GPU-accelerated operations to significantly reduce computation time (3) targeted adversarial input generation enabling modifications in favor of specific target classes, and (4) comprehensive experimental evaluation on contemporary sequential neural network architectures.
Our evaluation demonstrates substantial improvements over existing methods: up to 4.7× memory reduction compared to FGSM and up to 301× speedup over DeepFault while maintaining comparable adversarial input quality. All experiments complete within tens of seconds, demonstrating practical scalability for contemporary models.
Our evaluation demonstrates substantial improvements over existing methods: up to 4.7× memory reduction compared to FGSM and up to 301× speedup over DeepFault while maintaining comparable adversarial input quality. All experiments complete within tens of seconds, demonstrating practical scalability for contemporary models.
Subjects
Fault Localization
Neural Networks
Adversarial Input Generation
ModelPruning
DDC Class
004: Computer Sciences