Exploring the Efficacy of Learning Techniques in Model Extraction Attacks on Image Classifiers: A Comparative Study

• Published in: Applied sciences Vol. 14; no. 9; p. 3785
• Main Authors: Han, Dong, Babaei, Reza, Zhao, Shangqing, Cheng, Samuel
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2024
• Subjects: active learning; Algorithms; Classification; Comparative analysis; image classification; Intellectual property; Internet; Investigations; Learning strategies; Machine learning; Methods; model extraction attack; Neural networks; Performance evaluation; Privacy; Queries; reinforcement learning; Safety and security measures; security; synthetic data

In the rapidly evolving landscape of cybersecurity, model extraction attacks pose a significant challenge, undermining the integrity of machine learning models by enabling adversaries to replicate proprietary algorithms without direct access. This paper presents a comprehensive study on model extrac...