Detection of Abnormal Database Queries in Weighted Bipartite Graph
Jun Ji, Aifen Fang, Chenlu Qiu, Lei Zhao · 2018
In the era of big data, massive data has been accumulated in integrated application platform of traffic management of public security. Prevention of information leakage becomes an essential task for data security and privacy protection. This work formulates the detection of suspicious accounts involving in abnormal query behaviors as an anomaly detection problem in weighted bipartite graph. Outlier scores of two different anomaly detection approaches are computed, and the suspicion of each user account is combined by bagging with breadth-first search scheme. Experimental result on real dataset is given, demonstrating the effectiveness of our proposed anomaly detection approaches and enhancement of bagging.