17938794. SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER simplified abstract (Dell Products L.P.)
Contents
- 1 SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER
Organization Name
Inventor(s)
OFIR Ezrielev of Beer Sheva (IL)
NADAV Azaria of Beer Sheva (IL)
SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER - A simplified explanation of the abstract
This abstract first appeared for US patent application 17938794 titled 'SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING AN AUTOENCODER
Simplified Explanation
Methods and systems for anomaly detection in a distributed system are disclosed in this patent application. The system includes an anomaly detector and one or more data collectors. The anomaly detector uses an inference model, such as an autoencoder, to detect anomalies in the data collected by the data collectors. The inference model may need re-training for accurate anomaly detection, which can be done using the data collected from the data collectors. After anomaly detection and/or inference model re-training, the data is discarded to remove it from the anomaly detector.
- Anomaly detection in a distributed system
- System includes an anomaly detector and data collectors
- Anomaly detector uses an inference model, like an autoencoder, to detect anomalies
- Inference model may need re-training for accurate anomaly detection
- Data collected from data collectors used for re-training
- Data discarded after anomaly detection and/or re-training
Potential Applications
This technology can be applied in various industries where anomaly detection in distributed systems is crucial, such as cybersecurity, network monitoring, and industrial automation.
Problems Solved
This technology solves the problem of efficiently detecting anomalies in a distributed system, allowing for timely intervention and prevention of potential issues.
Benefits
The benefits of this technology include improved system reliability, early detection of anomalies, reduced downtime, and enhanced overall system performance.
Potential Commercial Applications
Potential commercial applications of this technology include offering anomaly detection services to companies in sectors like finance, healthcare, and telecommunications.
Possible Prior Art
One possible prior art for this technology could be traditional anomaly detection methods that may not be as efficient or accurate in detecting anomalies in distributed systems.
Unanswered Questions
1. How does the system handle false positives in anomaly detection? 2. What is the computational overhead of re-training the inference model for anomaly detection?
Original Abstract Submitted
Methods and systems for anomaly detection in a distributed system are disclosed. To manage anomaly detection, a system may include an anomaly detector and one or more data collectors. The anomaly detector may detect anomalies in data obtained from one or more of the data collectors using an inference model. The inference model may be an autoencoder trained to reconstruct data that is intended to match input data to an extent considered acceptable by the system. To accurately perform anomaly detection, the inference model may require re-training. Data collected from the one or more data collectors may be used to re-train the inference model as needed. Following anomaly detection and/or inference model re-training, the data may be discarded to remove the data from the anomaly detector.
