Saved in:
Bibliographic Details
Main Authors: Yadav, Umesh, Niroula, Suman, Gupta, Gaurav Kumar, Yadav, Bicky
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.02147
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929681508335616
author Yadav, Umesh
Niroula, Suman
Gupta, Gaurav Kumar
Yadav, Bicky
author_facet Yadav, Umesh
Niroula, Suman
Gupta, Gaurav Kumar
Yadav, Bicky
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50
Yadav, Umesh
Niroula, Suman
Gupta, Gaurav Kumar
Yadav, Bicky
Cryptography and Security
Machine Learning
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.
title Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2501.02147