【报告题目】Anomaly Detection and Identification of Natural Data using Benford's law;
【报告时间】 2018.04.19 10:00-11:30
【报告地点】科技楼502-2
【报告摘要】This talk will present an overview of the theory and applications of Benford's law for anomaly detection in natural data. Some examples will be highlighted including the detection of glare effect in images and classification of biometric images for privacy protection, as well as security attacks related to network traffic data. Recent research based on this law has further shown that consistent anomaly patterns could be achieved for different network attacks, leading to the potential identification/pattern recognition of various types of attacks. Moreover, Benford's law has also been successfully applied for the detection of Alzheimer's Disease based on Electroencephalogram (EEG) data and this will be highlighted in the presentation.