机器学习安全及隐私保护研究进展.

Machine learning security and privacy:a survey

机器学习作为实现人工智能的一种重要方法,在数据挖掘、计算机视觉、自然语言处理等领域得到广泛应用。随着机器学习应用的普及发展,其安全与隐私问题受到越来越多的关注。首先结合机器学习的一般过程,对敌手模型进行了描述。然后总结了机器学习常见的安全威胁,如投毒攻击、对抗攻击、询问攻击等,以及应对的防御方法,如正则化、对抗训练、防御精馏等。接着对机器学习常见的隐私威胁,如训练数据窃取、逆向攻击、成员推理攻击等进行了总结,并给出了相应的隐私保护技术,如同态加密、差分隐私。最后给出了亟待解决的问题和发展方向。

As an important method to implement artificial intelligence, machine learning technology is widely used in data mining, computer vision, natural language processing and other fields. With the development of machine learning, it brings amount of security and privacy issues which are getting more and more attention. Firstly, the ad-versary model was described according to machine learning. Secondly, the common security threats in machine learning was summarized, such as poisoning attacks, adversarial attacks, oracle attacks, and major defense methods such as regularization, adversarial training, and defense distillation. Then, privacy issues such were summarized as stealing training data, reverse attacks, and membership tests, as well as privacy protection technologies such as dif-ferential privacy and homomorphic encryption. Finally, the urgent problems and development direction were given in this field.