Voice Phishing Dataset
收藏资源简介:
该数据集由韩国交通大学的研究团队创建,旨在用于训练和评估语音钓鱼检测模型。数据集包含真实的语音钓鱼通话记录,以及由人类专家创建的模拟语音钓鱼通话记录。此外,还包括了大量非语音钓鱼通话记录,如金融咨询、日常对话等,用于提高检测模型的鲁棒性。数据集的总条数为1377条,其中包括219条真实语音钓鱼通话记录、35条由人类专家创建的模拟语音钓鱼通话记录,以及1223条非语音钓鱼通话记录。数据集的创建旨在解决语音钓鱼诈骗问题,并通过自然语言处理技术提高检测模型的准确性和鲁棒性。
This dataset was developed by a research team from Korea University of Transportation for the purpose of training and evaluating voice phishing detection models. It comprises real voice phishing call records, as well as simulated voice phishing call records created by human experts. Additionally, it includes a large volume of non-voice phishing call records such as financial advisory calls and daily conversations, to enhance the robustness of the detection models. The total number of records in this dataset is 1377, consisting of 219 real voice phishing call records, 35 simulated voice phishing call records created by human experts, and 1223 non-voice phishing call records. This dataset was created to address the issue of voice phishing scams, and to improve the accuracy and robustness of detection models via natural language processing technologies.




