# US 12,603,911 B2 · System for intelligent automated simulation of penetration testing and isolation of vulnerable distributed electronic data registers > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,603,911 B2 - Document ID: US12603911B2 - Status: Granted - Kind: B2 - Application number: 18/237,980 - Filed: 2023-08-25 - Published: 2025-02-27 - Granted: 2026-04-14 - Earliest claimed: 2023-08-25 - Assignees: Bank of America Corporation - Applicants: Bank of America Corporation - Inventors: Shailendra Singh; Krishna Rangarao Mamadapur - Web page: https://patentgrep.com/patent/US12603911B2 ## CPC - H04L 63/1433: {Vulnerability analysis} - H04L 63/205: {involving negotiation or determination of the one or more network security mechanisms to be used, e.g. by negotiation between the client and the server or between peers or by selection according to the capabilities of the entities involved (negotiation of communication capabilities H04L69/24)} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A system is provided for intelligent automated simulation of penetration testing and isolation of vulnerable distributed electronic data registers. In particular, the system may extract metadata regarding one or more nodes or sections of a distributed register. Based on the metadata, the system may generate a knowledge graph that may indicate the vulnerabilities associated with particular nodes, blocks, and/or sections of the distributed register. Based on the knowledge graph, the system may compute vulnerability scores for the various nodes, blocks, and/or sections, and generate a vulnerability heatmap based on the scores. The system may further be configured to allow a user to perform automatic simulated penetration tests on the vulnerable portions of the distributed register and/or execute one or more remediation process on such vulnerable portions. In this way, the system provides an efficient way to identify and remediate vulnerabilities within a distributed register. ## Claims ### Claim 1 A system for intelligent automated simulation of penetration testing and isolation of vulnerable distributed electronic data registers, the system comprising: a processing device; a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of: continuously monitoring a distributed register network to extract metadata associated with the distributed register network; based on the extracted metadata, constructing a knowledge graph comprising information regarding the distributed register network; detecting a change in the distributed register network based on the knowledge graph; using a machine learning algorithm, identifying a potential vulnerability in a portion of the distributed register network based on the change in the distributed register network wherein identifying the potential vulnerability comprises: computing a vulnerability score for each node, block, and network of the distributed register network; and generating a visual heatmap of the vulnerability scores comprising a scatter plot with each node, block, and network of the distributed register network represented by points within the scatter plot, wherein a size and a color of the points correspond to the vulnerability scores; generating a testing environment comprising a simulation of the portion of the distributed register network; executing penetration testing of the simulation based on the potential vulnerability; and based on results of the penetration testing, updating security rules associated with the distributed register network. ### Claim 2 (depends on 1) The system of claim 1, wherein the change in the distributed register network comprises at least one of an addition or removal of a node, a blockchain application update, or a change in a smart contract. ### Claim 3 (depends on 1) The system of claim 1, wherein the potential vulnerability is one of a consensus mechanism vulnerability, node vulnerability, encryption key vulnerability, or smart contract vulnerability. ### Claim 4 (depends on 1) The system of claim 1, wherein the machine learning algorithm comprises at least one of a long short-term memory (“LSTM”), generative adversarial network (“GAN”), or transformer. ### Claim 5 (depends on 1) The system of claim 1, wherein identifying the potential vulnerability comprises: computing a vulnerability score associated with the portion of the distributed register network; and detecting that the vulnerability score exceeds a predefined threshold. ### Claim 6 (depends on 1) The system of claim 1, wherein the testing environment is generated and the penetration testing is executed based on receiving an artificial intelligence (“AI”) based user input, the user input comprising one or more parameters for the penetration testing. ### Claim 7 (depends on 1) The system of claim 1, wherein the testing environment is a sandboxed virtual environment where the simulation of the portion of the distributed register network is a virtualized copy of components of the portion of the distributed register network. ### Claim 8 A computer program product for intelligent automated simulation of penetration testing and isolation of vulnerable distributed electronic data registers, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to perform the steps of: continuously monitoring a distributed register network to extract metadata associated with the distributed register network; based on the extracted metadata, constructing a knowledge graph comprising information regarding the distributed register network; detecting a change in the distributed register network based on the knowledge graph; using a machine learning algorithm, identifying a potential vulnerability in a portion of the distributed register network based on the change in the distributed register network, wherein identifying the potential vulnerability comprises: computing a vulnerability score for each node, block, and network of the distributed register network; and generating a visual heatmap of the vulnerability scores comprising a scatter plot with each node, block, and network of the distributed register network represented by points within the scatter plot, wherein a size and a color of the points correspond to the vulnerability scores; generating a testing environment comprising a simulation of the portion of the distributed register network; executing penetration testing of the simulation based on the potential vulnerability; and based on results of the penetration testing, updating security rules associated with the distributed register network. ### Claim 9 (depends on 8) The computer program product of claim 8, wherein the change in the distributed register network comprises at least one of an addition or removal of a node, a blockchain application update, or a change in a smart contract. ### Claim 10 (depends on 8) The computer program product of claim 8, wherein the potential vulnerability is one of a consensus mechanism vulnerability, node vulnerability, encryption key vulnerability, or smart contract vulnerability. ### Claim 11 (depends on 8) The computer program product of claim 8, wherein the machine learning algorithm comprises at least one of a long short-term memory (“LSTM”), generative adversarial network (“GAN”), or transformer. ### Claim 12 (depends on 8) The computer program product of claim 8, wherein identifying the potential vulnerability comprises: computing a vulnerability score associated with the portion of the distributed register network; and detecting that the vulnerability score exceeds a predefined threshold. ### Claim 13 (depends on 8) The computer program product of claim 8, wherein the testing environment is generated and the penetration testing is executed based on receiving an artificial intelligence (“AI”) based user input, the user input comprising one or more parameters for the penetration testing. ### Claim 14 A computer-implemented method for intelligent automated simulation of penetration testing and isolation of vulnerable distributed electronic data registers, the computer-implemented method comprising: continuously monitoring a distributed register network to extract metadata associated with the distributed register network; based on the extracted metadata, constructing a knowledge graph comprising information regarding the distributed register network; detecting a change in the distributed register network based on the knowledge graph; using a machine learning algorithm, identifying a potential vulnerability in a portion of the distributed register network based on the change in the distributed register network, wherein identifying the potential vulnerability comprises: computing a vulnerability score for each node, block, and network of the distributed register network; and generating a visual heatmap of the vulnerability scores comprising a scatter plot with each node, block, and network of the distributed register network represented by points within the scatter plot, wherein a size and a color of the points correspond to the vulnerability scores; generating a testing environment comprising a simulation of the portion of the distributed register network; executing penetration testing of the simulation based on the potential vulnerability; and based on results of the penetration testing, updating security rules associated with the distributed register network. ### Claim 15 (depends on 14) The computer-implemented method of claim 14, wherein the change in the distributed register network comprises at least one of an addition or removal of a node, a blockchain application update, or a change in a smart contract. ### Claim 16 (depends on 14) The computer-implemented method of claim 14, wherein the potential vulnerability is one of a consensus mechanism vulnerability, node vulnerability, encryption key vulnerability, or smart contract vulnerability. ### Claim 17 (depends on 14) The computer-implemented method of claim 14, wherein the machine learning algorithm comprises at least one of a long short-term memory (“LSTM”), generative adversarial network (“GAN”), or transformer. ### Claim 18 (depends on 14) The computer-implemented method of claim 14, wherein identifying the potential vulnerability comprises: computing a vulnerability score associated with the portion of the distributed register network; and detecting that the vulnerability score exceeds a predefined threshold. ### Claim 19 (depends on 14) The computer-implemented method of claim 14, wherein the testing environment is generated and the penetration testing is executed based on receiving an artificial intelligence (“AI”) based user input, the user input comprising one or more parameters for the penetration testing.