View source for 20240048570. Device and Method for Generating a Response to an Attack in a Communication Network Using Machine Learning simplified abstract (NOKIA TECHNOLOGIES OY)

=Device and Method for Generating a Response to an Attack in a Communication Network Using Machine Learning=


==Organization Name==

[[:Category:NOKIA TECHNOLOGIES OY|NOKIA TECHNOLOGIES OY]]


[[Category:NOKIA TECHNOLOGIES OY]]

==Inventor(s)==

[[:Category:Siwar Kriaa of Antony (FR)|Siwar Kriaa of Antony (FR)]][[Category:Siwar Kriaa of Antony (FR)]]

[[:Category:Afef Feki of Sceaux (FR)|Afef Feki of Sceaux (FR)]][[Category:Afef Feki of Sceaux (FR)]]

[[:Category:Arunkumar Halebid of Bangalore (IN)|Arunkumar Halebid of Bangalore (IN)]][[Category:Arunkumar Halebid of Bangalore (IN)]]

[[:Category:Serge Papillon of Paris (FR)|Serge Papillon of Paris (FR)]][[Category:Serge Papillon of Paris (FR)]]

==Device and Method for Generating a Response to an Attack in a Communication Network Using Machine Learning - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240048570 titled 'Device and Method for Generating a Response to an Attack in a Communication Network Using Machine Learning

==Simplified Explanation==

The abstract of this patent application describes a communication network device that is capable of predicting and detecting attacks based on data logs received from the network. The device generates graph representations of the data logs using a predefined schema. Attacks are detected by applying inference rules to the graph representations, while attacks are predicted using a graph neural network trained with subgraphs obtained from querying a graph representation of training data.

* The device is configured to predict and detect attacks in a communication network.
* Data logs received from the network are used to generate graph representations based on a predefined schema.
* Attacks are detected by applying inference rules to the graph representations of the data logs.
* Attacks are predicted using a graph neural network trained with subgraphs obtained from querying a graph representation of training data.
* The technology utilizes graph representations and inference rules to identify and respond to attacks in a communication network.

Potential Applications:
* Network security: This technology can be applied to enhance network security by predicting and detecting attacks in real-time, allowing for immediate response and mitigation.
* Intrusion detection systems: The device can be integrated into intrusion detection systems to improve their accuracy and effectiveness in identifying and responding to attacks.
* Cyber threat intelligence: The technology can contribute to the development of cyber threat intelligence systems by providing insights into attack patterns and trends.

Problems Solved:
* Timely attack detection: The device enables the timely detection of attacks by analyzing data logs and applying inference rules to identify suspicious patterns or behaviors.
* Attack prediction: By training a graph neural network with subgraphs obtained from training data, the device can predict attacks based on similarities to known attack patterns.
* Efficient response: The technology allows for a quick response to attacks upon prediction or detection, minimizing potential damage and reducing response time.

Benefits:
* Enhanced network security: The device improves the overall security of a communication network by predicting and detecting attacks, enabling proactive measures to be taken.
* Real-time threat response: With the ability to predict and detect attacks, the device facilitates real-time response, allowing for immediate action to mitigate the impact of attacks.
* Improved accuracy: By utilizing graph representations and inference rules, the technology enhances the accuracy of attack detection and prediction, reducing false positives and false negatives.


==Original Abstract Submitted==

in a communication network, a device is configured to predict attacks and detect attacks from data logs received from the network and generate a response to an attack upon prediction or detection of an attack. graph representations of data logs are generated based on a predefined schema. attacks are detected by applying inference rules to a graph representation of the data logs. attacks are predicted by using a graph neural network trained with subgraphs obtained by querying a graph representation of training data corresponding to normal traffic and attacks.



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