Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Undermining Image and Text Classification Algorithms Using Adversarial Attacks

Langalibalele Lunga, Suhas Sreehari

TL;DR

A 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy is observed, highlighting the susceptibility of these models to manipulation of input data.

Abstract

Machine learning models are prone to adversarial attacks, where inputs can be manipulated in order to cause misclassifications. While previous research has focused on techniques like Generative Adversarial Networks (GANs), there's limited exploration of GANs and Synthetic Minority Oversampling Technique (SMOTE) in text and image classification models to perform adversarial attacks. Our study addresses this gap by training various machine learning models and using GANs and SMOTE to generate additional data points aimed at attacking text classification models. Furthermore, we extend our investigation to face recognition models, training a Convolutional Neural Network(CNN) and subjecting it to adversarial attacks with fast gradient sign perturbations on key features identified by GradCAM, a technique used to highlight key image characteristics CNNs use in classification. Our experiments reveal a significant vulnerability in classification models. Specifically, we observe a 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy. This highlights the susceptibility of these models to manipulation of input data. Adversarial attacks not only compromise the security but also undermine the reliability of machine learning systems. By showcasing the impact of adversarial attacks on both text classification and face recognition models, our study underscores the urgent need for develop robust defenses against such vulnerabilities.

Undermining Image and Text Classification Algorithms Using Adversarial Attacks

TL;DR

A 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy is observed, highlighting the susceptibility of these models to manipulation of input data.

Abstract

Machine learning models are prone to adversarial attacks, where inputs can be manipulated in order to cause misclassifications. While previous research has focused on techniques like Generative Adversarial Networks (GANs), there's limited exploration of GANs and Synthetic Minority Oversampling Technique (SMOTE) in text and image classification models to perform adversarial attacks. Our study addresses this gap by training various machine learning models and using GANs and SMOTE to generate additional data points aimed at attacking text classification models. Furthermore, we extend our investigation to face recognition models, training a Convolutional Neural Network(CNN) and subjecting it to adversarial attacks with fast gradient sign perturbations on key features identified by GradCAM, a technique used to highlight key image characteristics CNNs use in classification. Our experiments reveal a significant vulnerability in classification models. Specifically, we observe a 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy. This highlights the susceptibility of these models to manipulation of input data. Adversarial attacks not only compromise the security but also undermine the reliability of machine learning systems. By showcasing the impact of adversarial attacks on both text classification and face recognition models, our study underscores the urgent need for develop robust defenses against such vulnerabilities.

Paper Structure

This paper contains 14 sections, 5 equations, 6 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Generative Adversarial Networks
  4. Synthetic Minority Oversampling Technique
  5. Adversarial Attacks/Data Generation with GANs
  6. Carlini Wagner Adversarial Attack
  7. Gradient-Weighted Class Activation Mapping
  8. Fast Gradient Sign Method
  9. Methodology
  10. Boundary point generation with SMOTE
  11. Boundary point generation with GANs
  12. GradCAM and Perturbations with FGSM
  13. Experiments and Results
  14. Conclusions

Figures (6)

  • Figure 1: Example SMOTE workflow on class balancing
  • Figure 2: First column are two input examples from the Olivetti Faces dataset (Row 1: Person 3 and Row 2 is Person 2). Second column are GradCAM heatmap of the activation maps. Third column shows the corresponding input GradCAM features that are key for CNN predictions.
  • Figure 3: Workflow for tabular data generation using GANs.
  • Figure 4: Input example faces and their true labels from the Olivetti dataset
  • Figure 5: CNN model architecture.
  • ...and 1 more figures