Using image conversion techniques to detect adversarial examples in machine learning models for tabular data

doi:10.1016/j.asoc.2025.113288

Using image conversion techniques to detect adversarial examples in machine learning models for tabular data

2025-06-04

0

PRE

AI

DOI：10.1016/j.asoc.2025.113288

Original

Original request for help

Save

Abstract

En 中文

• Employed unsupervised and supervised approaches for detecting adversarial examples. • Focused on machine learning models trained on tabular data. • Converted tabular data to images, leveraging the processing capabilities of deep learning techniques. • Leveraged explainability and transfer learning to enhance adversarial detection. • Achieved a detection rate of almost 100% on most of the examined datasets.

Keywords:

Security

Adversarial detection

Tabular data

Transfer learning

Image conversion

Using image conversion techniques to detect adversarial examples in machine learning models for tabular data

Abstract

Journal

Organization