Deep Anomaly Detection with Deviation Networks

19 Nov 2019  ·  Guansong Pang, Chunhua Shen, Anton Van Den Hengel ·

Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new feature representations to enable downstream anomaly detection methods, perform indirect optimization of anomaly scores, leading to data-inefficient learning and suboptimal anomaly scoring... Also, they are typically designed as unsupervised learning due to the lack of large-scale labeled anomaly data. As a result, they are difficult to leverage prior knowledge (e.g., a few labeled anomalies) when such information is available as in many real-world anomaly detection applications. This paper introduces a novel anomaly detection framework and its instantiation to address these problems. Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e.g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail. Extensive results show that our method can be trained substantially more data-efficiently and achieves significantly better anomaly scoring than state-of-the-art competing methods. read more

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Anomaly Detection Census DevNet AUC 0.828 # 2
Average Precision 0.321 # 1
Anomaly Detection Census AUC 2848.07 # 1
Fraud Detection Kaggle-Credit Card Fraud Dataset DevNet AUC 0.98 # 1
Average Precision 0.69 # 1
Network Intrusion Detection NB15-Backdoor DevNet AUC 0.969 # 1
Average Precision 0.883 # 1
Anomaly Detection Thyroid DevNet AUC 0.783 # 1
Average Precision 0.274 # 1

Methods


No methods listed for this paper. Add relevant methods here