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

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...

وصف كامل

التفاصيل البيبلوغرافية

الحاوية / القاعدة:	Applied Sciences
المؤلفون الرئيسيون:	Dong Han, Reza Babaei, Shangqing Zhao, Samuel Cheng
التنسيق:	مقال
اللغة:	الإنجليزية
منشور في:	MDPI AG 2024-04-01
الموضوعات:	synthetic data security active learning reinforcement learning model extraction attack image classification
الوصول للمادة أونلاين:	https://www.mdpi.com/2076-3417/14/9/3785