DC-VAE, Fine-grained Anomaly Detection in Multivariate Time-Series with Dilated Convolutions and Variational Auto Encoders.
Gastón García GonzálezSergio Martinez TagliaficoAlicia FernándezGabriel GómezJosé AcuñaPedro CasasPublished in: EuroS&P Workshops (2022)
Keyphrases
- anomaly detection
- fine grained
- multivariate time series
- coarse grained
- intrusion detection
- temporal data
- image segmentation
- dimension reduction
- categorical data
- access control
- temporal patterns
- intrusion detection system
- network traffic
- spatial structure
- optical flow
- unsupervised learning
- cluster analysis
- network security
- detect anomalies
- autoregressive
- data analysis
- feature extraction