A New Explainable Deep Learning Framework for Cyber Threat Discovery in Industrial IoT Networks

Keyphrases

• Cyber Threats 100%
• Deep Learning Framework 100%
• Industrial Internet of Things (IIoT) 100%
• Threat Discovery 100%
• Industrial IoT Network 100%
• Explainable Deep Learning 100%
• Sliding Window 60%
• Malicious Events 60%
• Quality of Service 40%
• Latent Representation 40%
• Administrators 20%
• Application Method 20%
• Industry 4.0 (I4.0) 20%
• Manufacturing Process 20%
• State-of-the-art Techniques 20%
• Network Use 20%
• Extracting Features 20%
• Data Accuracy 20%
• Detection Framework 20%
• Temporal Features 20%
• Contemporary State 20%
• Operative 20%
• Fixed-length 20%
• Sensing Device 20%
• Causal Reasoning 20%
• Data Representation 20%
• Utility Services 20%
• Data Integrity 20%
• Autoencoder 20%
• Internet of Things Networks 20%
• Data Poisoning Attack 20%
• Continuous-time 20%
• Fully Connected Network 20%
• Convolutional Networks 20%
• Industrial Utilities 20%
• Evaluation Metrics 20%
• Anomaly Recognition 20%
• Spatial Features 20%
• Multiple Evaluation 20%
• Heterogeneous Sensing 20%
• Industrial Machine 20%
• Time Critical Data 20%
• Recurrent Network 20%
• False Data Injection 20%
• Anomaly Explanation 20%

Computer Science

• Learning Framework 100%
• Deep Learning Method 100%
• Industrial Internet of Things 100%
• Sliding Window 60%
• Industry 4.0 20%
• Collected Data 20%
• Underlying Data 20%
• Utility Service 20%
• Connected Network 20%
• Data Integrity 20%
• Autoencoder 20%
• Continuous Time 20%
• Security Administrator 20%
• Evaluation Metric 20%
• Convolutional Network 20%
• Recurrent Network 20%