View source for 17938800. SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING ANOMALY THRESHOLDS BASED ON PROBABILITIES simplified abstract (Dell Products L.P.)

=SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING ANOMALY THRESHOLDS BASED ON PROBABILITIES=


==Organization Name==

[[:Category:Dell Products L.P.|Dell Products L.P.]]


[[Category:Dell Products L.P.]]

==Inventor(s)==

[[:Category:OFIR Ezrielev of Beer Sheva (IL)|OFIR Ezrielev of Beer Sheva (IL)]][[Category:OFIR Ezrielev of Beer Sheva (IL)]]

[[:Category:NADAV Azaria of Beer Sheva (IL)|NADAV Azaria of Beer Sheva (IL)]][[Category:NADAV Azaria of Beer Sheva (IL)]]

[[:Category:AVITAN Gefen of Tel Aviv (IL)|AVITAN Gefen of Tel Aviv (IL)]][[Category:AVITAN Gefen of Tel Aviv (IL)]]

==SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING ANOMALY THRESHOLDS BASED ON PROBABILITIES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17938800 titled 'SYSTEM AND METHOD FOR MEMORY-LESS ANOMALY DETECTION USING ANOMALY THRESHOLDS BASED ON PROBABILITIES

==Simplified Explanation==

Methods and systems for anomaly detection in a distributed environment are disclosed in the patent application. An anomaly detector and one or more data collectors work together to detect anomalies in data using an inference model and an anomaly threshold. The anomaly threshold is determined by fitting a normal distribution to the output of the inference model and may require periodic re-training of the inference model using data collected from the data collectors.

* Anomaly detection in a distributed environment
* Anomaly detector and data collectors collaborate
* Inference model and anomaly threshold used for detection
* Anomaly threshold determined by fitting a normal distribution
* Periodic re-training of the inference model using collected data

== Potential Applications ==
This technology can be applied in various industries such as cybersecurity, network monitoring, fraud detection, and predictive maintenance.

== Problems Solved ==
1. Early detection of anomalies in a distributed environment
2. Efficient management of anomaly detection using inference models and data collectors

== Benefits ==
1. Improved security and threat detection
2. Enhanced system performance and reliability
3. Cost-effective anomaly detection solution

== Potential Commercial Applications ==
Optimizing anomaly detection systems for cybersecurity companies

== Possible Prior Art ==
Prior art may include existing anomaly detection systems using machine learning algorithms and statistical analysis techniques.

== Unanswered Questions ==
=== How does the system handle false positives in anomaly detection? ===
The patent abstract does not mention how false positives are managed in the anomaly detection process.

=== What is the scalability of the system in terms of handling large volumes of data? ===
The scalability of the system in processing and analyzing large amounts of data is not addressed in the abstract.


==Original Abstract Submitted==

Methods and systems for anomaly detection in a distributed environment 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 and an anomaly threshold. The anomaly threshold may be determined by fitting a normal distribution to output of the inference model when the inference model is exercised across an input range of the inference model. The anomaly threshold may correspond to a portion of the normal distribution. To perform anomaly detection, the inference model may require periodic 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.



[[Category:H04L9/40]]
[[Category:H04L41/16]]