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 2108.08483cs.LG
收藏

基于多输入多输出Transformer的混合神经网络多类隐私泄露检测

A Multi-input Multi-output Transformer-based Hybrid Neural Network for Multi-class Privacy Disclosure Detection

Boise State University(博伊西州立大学)

A K M Nuhil Mehdy, Hoda Mehrpouyan

摘要:

由于通信平台、社交网站的大量增加,以及更多用户参与在线公共话语,对用户数据隐私的关注已上升到最高水平。越来越多的人通过电子邮件、短信和社交媒体交换私人信息,却没有意识到其中的风险和影响。自然语言处理(NLP)领域的研究人员一直致力于创建工具和策略来识别、分类和净化文本数据中的私有信息,因为大量的数据是以文本形式交换的。然而,大多数检测方法仅仅依赖于文本中预先识别的关键字的存在,而忽略了在特定上下文中对话语的潜在含义的推断。因此,在某些情况下,这些工具和算法无法检测到披露,或者产生的结果被错误分类。在本文中,我们提出了一个多输入,多输出的混合神经网络,利用迁移学习,语言学,和元数据来学习隐藏的模式。我们的目标是更好地分类披露/不披露内容的情况下的背景。我们在人工注释的地面实况数据集上训练和评估了我们的模型,该数据集总共包含5,400条推文。结果表明,该模型能够通过两个单独的任务联合学习,以77.4%的准确率识别通过推文的隐私泄露,同时以99%的准确率对这些推文的信息类型进行分类。

英文摘要:

The concern regarding users' data privacy has risen to its highest level due to the massive increase in communication platforms, social networking sites, and greater users' participation in online public discourse. An increasing number of people exchange private information via emails, text messages, and social media without being aware of the risks and implications. Researchers in the field of Natural Language Processing (NLP) have concentrated on creating tools and strategies to identify, categorize, and sanitize private information in text data since a substantial amount of data is exchanged in textual form. However, most of the detection methods solely rely on the existence of pre-identified keywords in the text and disregard the inference of the underlying meaning of the utterance in a specific context. Hence, in some situations, these tools and algorithms fail to detect disclosure, or the produced results are miss-classified. In this paper, we propose a multi-input, multi-output hybrid neural network which utilizes transfer-learning, linguistics, and metadata to learn the hidden patterns. Our goal is to better classify disclosure/non-disclosure content in terms of the context of situation. We trained and evaluated our model on a human-annotated ground truth dataset, containing a total of 5,400 tweets. The results show that the proposed model was able to identify privacy disclosure through tweets with an accuracy of 77.4% while classifying the information type of those tweets with an impressive accuracy of 99%, by jointly learning for two separate tasks.

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。

↑