Beekeeperai, Inc.

Alan Donald Czeszynski

Robert Derward Rogers

Mary Elizabeth Chalk

Systems and methods for data obfuscation are provided. Data obfuscation is needed when protecting an algorithm from reverse engineering attempts. The data is obfuscated by requesting more data from the data steward than is needed by the algorithm. If there are not enough types of data available from the data steward, 'low intensity' data types can be requested to fill out the data types requested. These 'low intensity' data types are ones that are easily obtained or even regularly collected anyway. The algorithms libraries are altered to call for all the data fields available, thereby rendering reverse engineering extremely difficult, if not impossible.

Systems and methods for data obfuscation in a zero-trust environment

Confirmation of data selection in a zero-trust environment is provided. In some embodiments, a synthetic data steward and/or a traditional data steward can receive the dataset(s). Additionally, a script is received from the algorithm developer. The dataset(s) and script(s) reside within a secure computing node and are therefore inaccessible by any party. The script(s) are executed, resulting in at least one confirmation about the data within the dataset(s). The script(s) complete any of confirming a format for data in the at least one dataset, the expected class values for data within the at least one dataset, an overall characterization and completeness of the at least one dataset, and/or an expected class membership for different data attributes within the at least one dataset.

Synthetic and traditional data stewards for selecting, optimizing, verifying and recommending one or more datasets

An algorithm is trained on a dataset to facilitate dynamic data exfiltration protection in a zero-trust environment. An inversion threat model using the original training dataset (a 'gold standard' inversion model) may also be generated. This inversion model can be characterized to determine its performance/accuracy of properly identifying a given input as being within the original training dataset or not (a data exfiltration event). It is possible to reduce this risk of data exfiltration to a desired level, without unduly impacting the algorithm's performance using the inversion model for the generation of noise that is targeted (as opposed to Gaussian noise). Noise added to the original training dataset causes the inversion model to perform poorer (meaning data steward data is more secure) but has a corresponding impact on the algorithm accuracy and performance. By adding noise generated by the inversion model in an iterative manner, and measuring the inversion model's performance, a balance can be reached where the data steward's data is considered secure, while minimizing the negative impact on the algorithm performance.

Growing community of inventors

Pleasanton, CA, United States of America

Alan Donald Czeszynski