arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.08151cs.CRcs.SI
收藏

在线评论系统中的自动众包攻击与防御

Automated Crowdturfing Attacks and Defenses in Online Review Systems

Yuanshun Yao, Bimal Viswanath, Jenna Cryan, Haitao Zheng, Ben Y. Zhao

摘要:

恶意众包论坛作为在线传播错误信息的来源越来越受到关注,但受到雇用和管理人类工人的成本的限制。在本文中,我们确定了一类新的攻击,这些攻击利用深度学习语言模型(递归神经网络或RNN)来自动生成产品和服务的虚假在线评论。这些攻击不仅成本低,因此更具可扩展性,而且它们可以控制内容输出的速率,以消除使众包活动易于检测的签名突发性。使用Yelp评论作为一个示例平台,我们展示了如何两个阶段的审查生成和定制攻击可以产生评论,是无法区分的国家的最先进的统计检测器。我们进行了一项基于调查的用户研究,以显示这些评论不仅可以逃避人类检测,而且在用户的“有用性”指标上得分很高。最后,我们通过利用RNN训练和生成周期引入的有损转换来开发针对这些攻击的新型自动防御。我们考虑对策对我们的机制,表明他们产生没有吸引力的成本效益权衡攻击者,他们可以进一步削减由在线服务提供商施加的简单约束。

英文摘要:

Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers. In this paper, we identify a new class of attacks that leverage deep learning language models (Recurrent Neural Networks or RNNs) to automate the generation of fake online reviews for products and services. Not only are these attacks cheap and therefore more scalable, but they can control rate of content output to eliminate the signature burstiness that makes crowdsourced campaigns easy to detect. Using Yelp reviews as an example platform, we show how a two phased review generation and customization attack can produce reviews that are indistinguishable by state-of-the-art statistical detectors. We conduct a survey-based user study to show these reviews not only evade human detection, but also score high on "usefulness" metrics by users. Finally, we develop novel automated defenses against these attacks, by leveraging the lossy transformation introduced by the RNN training and generation cycle. We consider countermeasures against our mechanisms, show that they produce unattractive cost-benefit tradeoffs for attackers, and that they can be further curtailed by simple constraints imposed by online service providers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑