20230118857. PEER RISK BENCHMARKING USING GENERATIVE ADVERSARIAL NETWORKS simplified abstract (Cisco Technology, Inc.)
PEER RISK BENCHMARKING USING GENERATIVE ADVERSARIAL NETWORKS
Organization Name
Inventor(s)
Qihong Shao of Clyde Hill WA (US)
David John Zacks of Vancouver (CA)
Xinjun Zhang of San Jose CA (US)
PEER RISK BENCHMARKING USING GENERATIVE ADVERSARIAL NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230118857 titled 'PEER RISK BENCHMARKING USING GENERATIVE ADVERSARIAL NETWORKS
Simplified Explanation
The abstract describes a method, computer system, and computer program product for peer risk benchmarking. It involves obtaining customer data for a first network, which includes the role of network devices and risk reports associated with different dimensions of risk. A network profile image is generated by processing the risk reports. A generative adversarial network then creates a synthetic network profile image without customer data. The synthetic image is used to evaluate a second network and identify differences with the first network.
- Obtaining customer data for a network and risk reports for network devices
- Generating a network profile image by processing the risk reports
- Creating a synthetic network profile image without customer data
- Evaluating a second network using the synthetic image to identify differences with the first network
Potential Applications
- Network security: Assessing the risk of different networks and identifying areas for improvement.
- Network optimization: Comparing networks to find areas of inefficiency or potential upgrades.
- Risk management: Providing insights into potential vulnerabilities and helping organizations prioritize their risk mitigation efforts.
Problems Solved
- Lack of benchmarking: This technology allows for the comparison of different networks to identify differences and potential areas for improvement.
- Privacy concerns: By generating a synthetic network profile image without customer data, privacy is protected while still allowing for evaluation and benchmarking.
Benefits
- Improved network security: By identifying differences between networks, organizations can better understand their own vulnerabilities and take steps to enhance security.
- Efficient resource allocation: Benchmarking networks helps organizations allocate resources effectively by identifying areas that require attention or investment.
- Privacy protection: The use of synthetic network profile images ensures that customer data is not exposed during the evaluation and benchmarking process.
Original Abstract Submitted
a method, computer system, and computer program product are provided for peer risk benchmarking. customer data for a first network is obtained, wherein the customer data comprises a role of one or more network devices in the first network and a plurality of risk reports corresponding to the one or more network devices, and wherein each risk report is associated with a particular dimension of a plurality of dimensions of risk for the one or more network devices. a network profile image is generated by processing the plurality of risk reports. a generative adversarial network generates a synthetic network profile image from the network profile image, wherein the synthetic network profile image does not include the customer data. a second network is evaluated using the synthetic network profile image to identify differences between the first network and the second network.
