Social networks have become an indispensable part of our lives, with billions
of people producing ever-increasing amounts of text. At such scales, content
policies and their enforcement become paramount. To automate moderation,
questionable content is detected by Natural Language Processing (NLP)
classifiers. However, high-performance classifiers are hampered by misspellings
and adversarial text perturbations. In this paper, we classify intentional and
unintentional adversarial text perturbation into ten types and propose a
deobfuscation pipeline to make NLP models robust to such perturbations. We
propose Continuous Word2Vec (CW2V), our data-driven method to learn word
embeddings that ensures that perturbations of words have embeddings similar to
those of the original words. We show that CW2V embeddings are generally more
robust to text perturbations than embeddings based on character ngrams. Our
robust classification pipeline combines deobfuscation and classification, using
proposed defense methods and word embeddings to classify whether Facebook posts
are requesting engagement such as likes. Our pipeline results in engagement
bait classification that goes from 0.70 to 0.67 AUC with adversarial text
perturbation, while character ngram-based word embedding methods result in
downstream classification that goes from 0.76 to 0.64.

本文提出了一种使用 deobfuscation 和 CW2V 嵌入的强健分类管道，用于检测 Facebook 帖子是否请求参与（例如点赞）。在针对有意和无意的对抗文本扰动方面，CW2V 嵌入的强健性优于基于字符 ngram 的嵌入，其分类结果在扰动下的 AUC 从 0.70 降至 0.67，而字符 ngram 嵌入的分类结果从 0.76 降至 0.64。