Abstract: Identifying code has been widely used in man-machine verification to maintain network security. The challenge in engaging man-machine verification involves the correct classification of man and machine tracks. In this study, we propose a random forest (RF) model for man-machine verification based on the mouse movement trajectory dataset. We also compare the RF model with the baseline models (logistic regression and support vector machine) based on performance metrics such as precision, recall, false positive rates, false negative rates, F-measure, and weighted accuracy. The performance metrics of the RF model exceed those of the baseline models.

基于随机森林模型的滑动轨迹人机识别

[1]Brown M, Rogers SJ, 1993. User identification via keystroke characteristics of typed names using neural networks. Int J Man-Mach Stud, 39(6):999-1014.

[2]Caruana R, Niculescu-Mizil A, 2006. An empirical comparison of supervised learning algorithms. 23^rd Int Conf on Machine Learning, p.161-168.

[3]Chen C, Liaw A, Breiman L, 2004. Using Random Forest to Learn Imbalanced Data. Technical Report No. 666, University of California, Berkeley.

[4]De’ath G, Fabricius KE, 2000. Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology, 81(11):3178-3192.

[5]Gordon LA, Loeb MP, Lucyshyn W, et al., 2006. 2006 CSI/FBI Computer Crime and Security Survey. Computer Security Institute, USA.

[6]Hultquist C, Chen G, Zhao KG, 2014. A comparison of Gaussian process regression, random forests and support vector regression for burn severity assessment in diseased forests. Remote Sens Lett, 5(8):723-732.

[7]Liu L, Yang AL, Zhou WJ, et al., 2015. Robust dataset classification approach based on neighbor searching and kernel fuzzy c-means. IEEE/CAA J Autom Sin, 2(3):235-247.

[8]Sanjaa B, Chuluun E, 2013. Malware detection using linear SVM. 8^th Int Forum on Strategic Technology, p.136-138.

[9]Su T, 2016. Application of CAPTCHA with Behavioral Vilification Based on GBDT. MS Thesis, Central China Normal University, Wuhan, China (in Chinese).

[10]Taieb SB, Hyndman RJ, 2014. A gradient boosting approach to the Kaggle load forecasting competition. Int J Forecast, 30(2):382-394.

[11]Weiss A, Ramapanicker A, Shah P, et al., 2007. Mouse movements biometric identification: a feasibility study. Proc Student/Faculty Research Day.