你所需要的只是“爱”：逃避仇恨语言检测
All You Need is "Love": Evading Hate-speech Detection
摘要：
随着社交网络的传播及其被不幸地用于仇恨言论，对后者的自动检测已成为一个紧迫的问题。在本文中，我们重现了七个国家的最先进的仇恨言论检测模型从以前的工作，并表明，他们只有在测试时，他们是训练在相同类型的数据，基于这些结果，我们认为，对于成功的仇恨言论检测，模型架构是不重要的数据类型和标记标准。我们进一步表明，所有提出的检测技术是脆弱的对手谁可以（自动）插入错别字，改变词的边界或添加无害的话，原来的仇恨言论。这些方法的组合对Google Perspective也很有效--这是一个来自行业的尖端解决方案。我们的实验表明，对抗性训练并不能完全减轻攻击，使用字符级特征可以使模型比使用单词级特征更系统地抵抗攻击。
英文摘要：
With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven state-of-the-art hate speech detection models from prior work, and show that they perform well only when tested on the same type of data they were trained on. Based on these results, we argue that for successful hate speech detection, model architecture is less important than the type of data and labeling criteria. We further show that all proposed detection techniques are brittle against adversaries who can (automatically) insert typos, change word boundaries or add innocuous words to the original hate speech. A combination of these methods is also effective against Google Perspective -- a cutting-edge solution from industry. Our experiments demonstrate that adversarial training does not completely mitigate the attacks, and using character-level features makes the models systematically more attack-resistant than using word-level features.
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。
