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 2205.01362cs.LG
收藏

TracInAD:面向异常检测的影响力度量方法

TracInAD: Measuring Influence for Anomaly Detection

Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);CentraleSupélec(中央理工-高等电力学院);Lusis(Lusis公司)

Hugo Thimonier, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan, Fabrice Daniel

AI总结:

针对表格数据集深度异常检测模型匮乏的问题,本文提出基于TracIn影响力度量的TracInAD方法,可增强任意无监督深度异常检测模型,在医疗、网络安全表格基准上检测精度达到或优于现有最优水平。

摘要:

与诸多其他任务一样,神经网络在异常检测任务中表现出极强的有效性,但目前极少有深度学习模型适用于表格数据集的异常检测。本文提出一种基于TracIn(一种最初为可解释性提出的影响力度量方法)标记异常的全新方法,该方法可作为任意无监督深度异常检测方法的增强方案。我们使用变分自编码器(Variational Autoencoders)对所提方法进行测试,结果表明,训练点子样本对测试点的平均影响力可作为异常程度的代理指标。该模型性能与当前最优方法相当:在医疗和网络安全领域的表格基准数据集上,其检测精度达到了可比甚至更优的水平。

英文摘要:

As with many other tasks, neural networks prove very effective for anomaly detection purposes. However, very few deep-learning models are suited for detecting anomalies on tabular datasets. This paper proposes a novel methodology to flag anomalies based on TracIn, an influence measure initially introduced for explicability purposes. The proposed methods can serve to augment any unsupervised deep anomaly detection method. We test our approach using Variational Autoencoders and show that the average influence of a subsample of training points on a test point can serve as a proxy for abnormality. Our model proves to be competitive in comparison with state-of-the-art approaches: it achieves comparable or better performance in terms of detection accuracy on medical and cyber-security tabular benchmark data.

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。

↑