TSI-GAN: Unsupervised Time Series Anomaly Detection using Convolutional Cycle-Consistent Generative Adversarial Networks. (arXiv:2303.12952v1 [cs.LG])

Anomaly detection is widely used in network intrusion detection, autonomous
driving, medical diagnosis, credit card frauds, etc. However, several key
challenges remain open, such as lack of ground truth labels, presence of
complex temporal patterns, and generalizing over different datasets. This paper
proposes TSI-GAN, an unsupervised anomaly detection model for time-series that
can learn complex temporal patterns automatically and generalize well, i.e., no
need for choosing dataset-specific parameters, making statistical assumptions
about underlying data, or changing model architectures. To achieve …

adversarial anomaly detection autonomous autonomous driving card challenges credit credit card datasets detection driving etc gan generative generative adversarial networks intrusion intrusion detection key key challenges learn medical network networks patterns series temporal truth