Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects

Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects
复制标题

智能网络中毒攻击及对策:现状与前景

DOI:
10.1016/j.dcan.2021.07.009
复制
发表时间:
2021-07
影响因子:
7.9
通讯作者:
Liu Jiangchuan
Liu Jiangchuan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Wang Chen;Chen Jian;Yang Yang;Ma Xiaoqiang;Liu Jiangchuan

文献摘要

参考文献

被引文献

相似文献

在过去的几年里,以机器学习技术为动力的智能网络的出现给人类生活的各个方面带来了极大的便利。然而,在智能网络中使用机器学习也会带来潜在的安全和隐私威胁。一种常见的做法是所谓的中毒攻击,即恶意用户注入虚假的训练数据,目的是破坏学习的模型。在本次调查中,我们首次全面回顾了智能网络中现有的中毒攻击以及应对措施。重点比较了形式化中毒攻击在不同类别学习算法中的应用原理,并以紧凑的形式分析了相应防御方法的优点和局限性。我们还强调了攻防对抗中的一些剩余挑战和未来方向,以促进这一新兴但有前途的领域的进一步研究。
Over the past years, the emergence of intelligent networks empowered by machine learning techniques has brought great facilitates to different aspects of human life. However, using machine learning in intelligent networks also presents potential security and privacy threats. A common practice is the so-called poisoning attacks where malicious users inject fake training data with the aim of corrupting the learned model. In this survey, we comprehensively review existing poisoning attacks as well as the countermeasures in intelligent networks for the first time. We emphasize and compare the principles of the formal poisoning attacks employed in different categories of learning algorithms, and analyze the strengths and limitations of corresponding defense methods in a compact form. We also highlight some remaining challenges and future directions in the attack-defense confrontation to promote further research in this emerging yet promising area.
DOI: 10.1007/978-3-030-13453-2_1
发表时间: 2018-03
期刊: ArXiv
影响因子: --
作者:
Andrea Paudice;Luis Muñoz-González;Emil C. Lupu
通讯作者: Andrea Paudice;Luis Muñoz-González;Emil C. Lupu
DOI: --
发表时间: 2018-03
期刊: ArXiv
影响因子: --
作者:
Octavian Suciu;R. Marginean;Yigitcan Kaya;Hal Daumé;Tudor Dumitras
通讯作者: Octavian Suciu;R. Marginean;Yigitcan Kaya;Hal Daumé;Tudor Dumitras
DOI: 10.1109/mcom.2014.6736752
发表时间: 2014-02-01
影响因子: 11.2
作者:
Wang, Cheng-Xiang;Haider, Fourat;Hepsaydir, Erol
通讯作者: Hepsaydir, Erol
DeepScan:利用深度学习在基于位置的社交网络中检测恶意帐户
DOI: --
发表时间: 2018
影响因子: 11.2
作者:
Qingyuan Gong;Yang Chen;Xinlei He;Zhuang Zhou;Tianyi Wang;Hong Huang;Xin Wang;Xiaoming Fu
通讯作者: Xiaoming Fu
DOI: 10.1109/tkde.2013.57
发表时间: 2014-04-01
影响因子: 8.9
作者:
Biggio, Battista;Fumera, Giorgio;Roli, Fabio
通讯作者: Roli, Fabio