Attacking Fake News Detectors via Manipulating News Social Engagement
Attacking Fake News Detectors via Manipulating News Social Engagement
复制标题
DOI：
10.1145/3543507.3583868
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Haoran Wang;Yingtong Dou;Canyu Chen;Lichao Sun;Philip S. Yu;Kai Shu
中科院分区：
文献类型：
--
作者：
Haoran Wang;Yingtong Dou;Canyu Chen;Lichao Sun;Philip S. Yu;Kai Shu
社交媒体是新闻消费的主要来源之一，尤其是年轻一代。随着各种社交媒体平台上新闻消费的日益普及，包括虚假信息或毫无根据的主张在内的错误信息激增。随着各种基于文本和社交上下文的假新闻检测器被提出来检测社交媒体上的错误信息，最近的工作开始关注假新闻检测器的漏洞。在本文中，我们提出了第一个针对基于图神经网络（GNN）的假新闻检测器的对抗性攻击框架，以探讨其鲁棒性。具体来说，我们利用多代理强化学习（MARL）框架来模拟社交媒体上欺诈者的对抗行为。研究表明，在现实世界中，欺诈者会相互协调分享不同的新闻，以逃避假新闻检测器的检测。因此，我们将 MARL 框架建模为具有机器人、机器人和众包代理的马尔可夫博弈，它们有自己独特的成本、预算和影响力。然后，我们使用深度 Q 学习来搜索最大化奖励的最优策略。对两个真实世界假新闻传播数据集的大量实验结果表明，我们提出的框架可以有效地破坏基于 GNN 的假新闻检测器的性能。我们希望本文能为未来假新闻检测的研究提供见解。
Social media is one of the main sources for news consumption, especially among the younger generation. With the increasing popularity of news consumption on various social media platforms, there has been a surge of misinformation which includes false information or unfounded claims. As various text- and social context-based fake news detectors are proposed to detect misinformation on social media, recent works start to focus on the vulnerabilities of fake news detectors. In this paper, we present the first adversarial attack framework against Graph Neural Network (GNN)-based fake news detectors to probe their robustness. Specifically, we leverage a multi-agent reinforcement learning (MARL) framework to simulate the adversarial behavior of fraudsters on social media. Research has shown that in real-world settings, fraudsters coordinate with each other to share different news in order to evade the detection of fake news detectors. Therefore, we modeled our MARL framework as a Markov Game with bot, cyborg, and crowd worker agents, which have their own distinctive cost, budget, and influence. We then use deep Q-learning to search for the optimal policy that maximizes the rewards. Extensive experimental results on two real-world fake news propagation datasets demonstrate that our proposed framework can effectively sabotage the GNN-based fake news detector performance. We hope this paper can provide insights for future research on fake news detection.