17643498. ADAPTIVE NETWORK CONTROL OF TRAFFIC FLOWS IN A SECURE NETWORK simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
ADAPTIVE NETWORK CONTROL OF TRAFFIC FLOWS IN A SECURE NETWORK
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Szymon Kowalczyk of Krakow (PL)
Marcel Butucea Panait of Brno (CZ)
ADAPTIVE NETWORK CONTROL OF TRAFFIC FLOWS IN A SECURE NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 17643498 titled 'ADAPTIVE NETWORK CONTROL OF TRAFFIC FLOWS IN A SECURE NETWORK
Simplified Explanation
The patent application describes a method for rate limiting in a network using supervised and unsupervised learning techniques. Here are the key points:
- The method starts by receiving a traffic flow from the network.
- In the supervised learning phase, the traffic flow is compared to a pretrained network flow model to determine if it matches.
- If a match is found, the traffic flow is classified according to the pretrained model.
- If no match is found, the method advances to the unsupervised learning phase.
- In the unsupervised learning phase, the traffic flow is classified as a classified traffic flow.
- After the supervised and unsupervised learning phases, the method enters a grouping phase.
- In the grouping phase, side information about the traffic flows is used to group related traffic flows together.
- The method identifies a particular traffic flow group as an offending traffic flow group.
- The method can be used to effectively rate limit network traffic and identify potential threats or abnormal behavior.
Potential applications of this technology:
- Network traffic management and optimization
- Network security and threat detection
- Quality of Service (QoS) control in networks
Problems solved by this technology:
- Efficiently categorizing and classifying network traffic flows
- Identifying and isolating offending traffic flow groups
- Enhancing network performance and security
Benefits of this technology:
- Improved network traffic management and control
- Enhanced network security and threat detection capabilities
- More efficient allocation of network resources
- Better overall network performance and user experience.
Original Abstract Submitted
A method is provided for rate limiting in a network. The method comprises receiving a traffic flow from the network. In a supervised learning phase, and determining if the traffic flow matches a pretrained network flow model. If so, the method comprises designating the traffic flow as a classified traffic flow according to the pretrained network flow model. The method further comprises advancing to a grouping phase, conditioned upon the traffic flow not matching pretrained network flow models. In the unsupervised learning phase, the method comprises designating the traffic flow as a classified traffic flow. In the grouping phase that follows the supervised learning phase and the unsupervised learning phase, the method comprises using side information about the traffic flows to assign related traffic flows into traffic flow groups, identifying a particular traffic flow group from the traffic flow groups as being an offending traffic flow group.