# Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50

Source: [Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50](<https://www.sota2.com/research/paper/68fa76ae1e209131cea6e685>)

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

Data updated: 2025-10-27T06:45:57.319Z

Authors: Umesh Yadav, Suman Niroula, Gaurav Kumar Gupta, Bicky Yadav

Published: 2025-01-04T00:21:23.000Z

## 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.

## 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/2501.02147>)

[PDF](<https://arxiv.org/pdf/2501.02147.pdf>)