Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50
Abstract
This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a 53.33% accuracy on clean images. When subjected to FGSM perturbations, its overall accuracy remains unchanged; however, the model's confidence in incorrect predictions notably increases. Concurrently, a payload injection scheme is successfully executed in 93.33% of the tested samples, revealing how stealthy attacks can manipulate model predictions without degrading visual quality. These findings underscore the vulnerability of even high-performing neural networks and highlight the urgency of developing more robust defense mechanisms for security-critical applications.
Cite
@article{arxiv.2501.02147,
title = {Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50},
author = {Umesh Yadav and Suman Niroula and Gaurav Kumar Gupta and Bicky Yadav},
journal= {arXiv preprint arXiv:2501.02147},
year = {2025}
}