Empirical study of privacy inference attack against deep reinforcement learning models

Most studies on privacy in machine learning have primarily focused on supervised learning, with little research on privacy concerns in reinforcement learning. However, our study has demonstrated that observation information can be extracted through trajectory analysis. In this paper, we propose a va...

وصف كامل

التفاصيل البيبلوغرافية
الحاوية / القاعدة:Connection Science
المؤلفون الرئيسيون: Huaicheng Zhou, Kanghua Mo, Teng Huang, Yongjin Li
التنسيق: مقال
اللغة:الإنجليزية
منشور في: Taylor & Francis Group 2023-12-01
الموضوعات:
reinforcement learning
privacy attack
deep learning
data security
adversarial attack
الوصول للمادة أونلاين:http://dx.doi.org/10.1080/09540091.2023.2211240

الانترنت

http://dx.doi.org/10.1080/09540091.2023.2211240

مواد مشابهة