当前位置: X-MOL 学术IEEE Internet Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Approaches for Fake Content Detection: Strengths and Weaknesses to Adversarial Attacks
IEEE Internet Computing ( IF 3.7 ) Pub Date : 2020-01-01 , DOI: 10.1109/mic.2020.3032323
Matthew Carter 1 , Michail Tsikerdekis 1 , Sherali Zeadally 2
Affiliation  

In the last few years, we have witnessed an explosive growth of fake content on the Internet which has significantly affected the veracity of information on many social platforms. Much of this disruption has been caused by the proliferation of advanced machine and deep learning methods. In turn, social platforms have been using the same technological methods in order to detect fake content. However, there is understanding of the strengths and weaknesses of these detection methods. We describe examples of machine and deep learning approaches that can be used to detect different types of fake content. We also discuss the characteristics and the potential for adversarial attacks on these methods that could reduce the accuracy of fake content detection. Finally, we identify and discuss some future research challenges in this area.

中文翻译:

虚假内容检测方法:对抗性攻击的优缺点

在过去几年中,我们目睹了互联网上虚假内容的爆炸式增长,这对许多社交平台上的信息真实性造成了显着影响。这种破坏在很大程度上是由先进的机器和深度学习方法的激增造成的。反过来,社交平台一直在使用相同的技术方法来检测虚假内容。但是,人们对这些检测方法的优缺点有所了解。我们描述了可用于检测不同类型虚假内容的机器和深度学习方法的示例。我们还讨论了这些方法的特征和对抗性攻击的可能性,这些方法可能会降低虚假内容检测的准确性。最后,我们确定并讨论了该领域未来的一些研究挑战。
更新日期:2020-01-01
down
wechat
bug