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 2203.06793cs.CL
收藏

预训练的Transformers能用于检测复杂敏感句子吗?--孟山都案例研究

Can pre-trained Transformers be used in detecting complex sensitive sentences? -- A Monsanto case study

UNSW Sydney(新南威尔士大学悉尼分校);Data61 Cyber Security CRC(Data61网络安全合作研究中心);Penten(Penten公司)

Roelien C. Timmer, David Liebowitz, Surya Nepal, Salil S. Kanhere

摘要:

每个组织都以各种形式发布信息,从年度报告到法律诉讼。这些文件可能包含敏感信息,公开发布可能导致机密信息泄露。检测文档中包含敏感信息的句子可以帮助组织防止有价值的机密信息泄露。当这些句子包含大量信息或是已知敏感内容的释义版本时,这尤其具有挑战性。在这种复杂设置中检测敏感信息的当前方法基于基于关键字的方法或标准机器学习模型。在本文中,我们希望探讨预训练的Transformer模型是否非常适合检测复杂的敏感信息。预先训练的Transformers通常在大量文本上进行训练,因此很容易学习语法,结构和其他语言特征,这使得它们对这项任务特别有吸引力。通过对Monsanto试验数据集的实验,我们观察到经过微调的双向编码器表示Transformers(BERT)Transformer模型比传统模型表现得更好。我们对Monsanto数据集中的四种不同类别的文档进行了实验,观察到与现有的敏感信息检测模型相比,BERT在GHOST、TOXIC、CHEMI和REGUL中分别获得了24.13%至65.79%、30.14%至54.88%、39.22%和53.57%的F2分数。

英文摘要:

Each and every organisation releases information in a variety of forms ranging from annual reports to legal proceedings. Such documents may contain sensitive information and releasing them openly may lead to the leakage of confidential information. Detection of sentences that contain sensitive information in documents can help organisations prevent the leakage of valuable confidential information. This is especially challenging when such sentences contain a substantial amount of information or are paraphrased versions of known sensitive content. Current approaches to sensitive information detection in such complex settings are based on keyword-based approaches or standard machine learning models. In this paper, we wish to explore whether pre-trained transformer models are well suited to detect complex sensitive information. Pre-trained transformers are typically trained on an enormous amount of text and therefore readily learn grammar, structure and other linguistic features, making them particularly attractive for this task. Through our experiments on the Monsanto trial data set, we observe that the fine-tuned Bidirectional Encoder Representations from Transformers (BERT) transformer model performs better than traditional models. We experimented with four different categories of documents in the Monsanto dataset and observed that BERT achieves better F2 scores by 24.13\% to 65.79\% for GHOST, 30.14\% to 54.88\% for TOXIC, 39.22\% for CHEMI, 53.57\% for REGUL compared to existing sensitive information detection models.

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。

↑