Cryptographic key control based on debasing condition likelihood estimation
US11463254B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 22, 2019 |
| Grant date | Oct 4, 2022 |
| Priority date | — |
| Expiry date | Jun 16, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In representative embodiments, systems and methods to calculate the likelihood that presented cryptographic key material is untrustworthy are disclosed. A predictive model based on a debasing condition and a dataset is created by evaluating the dataset relative to the debasing condition. For example, if certificate revocation is selected as the debasing condition, the dataset is analyzed to produce a predictive model that determines the likelihood that a presented certificate is untrustworthy based on similarity to already revoked certificates. The predictive model can include a supervised learning model like a logistic regression model or a deep neural network model. The system can be used in conjunction with existing security infrastructures or can be used as a separate infrastructure. Based on the likelihood score calculated by the model, a relying system can reject the cryptographic key material, accept the cryptographic key material or take other further action.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.