原文传递
Cyber Data Anomaly Detection Using Autoencoder Neural Networks.
| 题名： | Cyber Data Anomaly Detection Using Autoencoder Neural Networks. |
| 作者： | Butt, S. A. |
| 关键词： | Intrusion detection, Anomaly detection, Artificial neural networks, Computer network security, Regression analysis, Cyber anomaly detection, Autoencoder, Intrusion protection, Ann (artificial neural networks), Hyperparameter screening, Hyperparameter optimization, Idps (intrusion detection and intrusion prevention systems), Outliers, Uann (undercomplete autoencoder neural network) |
| 摘要： | The Department of Defense requires a secure presence in the cyber domain to successfully execute its stated mission of deterring war and protecting the security of the United States. With potentially millions of logged network events occurring on defended networks daily, a limited staff of cyber analysts require the capability to identify novel network actions for security adjudication. The detection methodology proposed uses an autoencoder neural network optimized via design of experiments for the identification of anomalous network events. Once trained, each logged network event is analyzed by the neural network and assigned an outlier score. The network events with the largest outlier scores are anomalous and worthy of further review by cyber analysts. This neural network approach can operate in conjunction with alternate tools for outlier detection, enhancing the overall anomaly detection capability of cyber analysts. |
| 报告类型： | 科技报告 |
相关文献
- Anomaly Detection for the Naval Smart Grid System Using Autoencoder Neural Networks.
- Autoencoded Reduced Clusters for Anomaly Detection Enrichment (ARCADE) in Hyperspectral Imagery.
- ARTIFICIAL NEURAL NETWORKS FOR FREEWAY INCIDENT DETECTION.
- REAL-TIME DATA FUSION FOR ARTERIAL STREET INCIDENT DETECTION USING NEURAL NETWORKS.
- Preprocessing Techniques to Support Event Detection Data Fusion on Social Media Data.
- USING ARTIFICIAL NEURAL NETWORKS AS A FORWARD APPROACH TO BACKCALCULATION.
检索历史
应用推荐
