No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection.
Mohamed YousefMarcel AckermannUnmesh KurupTom E. BishopPublished in: CoRR (2022)
Keyphrases
- anomaly detection
- intrusion detection
- unsupervised anomaly detection
- anomalous behavior
- detecting anomalies
- network intrusion detection
- intrusion detection system
- one class support vector machines
- malware detection
- behavior analysis
- negative selection algorithm
- network anomaly detection
- unsupervised learning
- network security
- detect anomalies
- network traffic
- computer security
- data sets
- maximum entropy
- computer systems
- detecting anomalous
- cumulative sum
- similarity measure