Back to results
US 11,113,579 B2Granted
Machine learning model score obfuscation using step function, position-dependent noise
AssigneeCylance Inc.
InventorsHailey Buckingham, David N. Beveridge
Life of this patent
Estimating the term…
Abstract
An artefact is received. Features are extracted from this artefact which are, in turn, used to populate a vector. The vector is then input into a classification model to generate a score. The score is then modified using a step function so that the true score is not obfuscated. Thereafter, the modified score can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.
Claims19
A computerimplernented method for obfuscating a score generated by a classification model comprising:
- receiving a vector comprising features extracted from an artefact;
- inputting the vector into a classification model to generate a score;
- modifying the score using a step function;
- wherein the step function applies position-dependent noise to the score;
- providing the modified score to a consuming application or process.
2 more elements
A system comprising:
- at least one data processor;
- and
- memory storing instructions which, when executed by the at least one data processor, result in operations comprising:
- receiving a vector comprising features extracted from an artefact;
- inputting the vector into a classification model to generate a score;
- modifying the score by applying position-dependent noise to the generated score;
- and
- providing the modified score to a consuming application or process.
5 more elements
A computer-implemented method comprising:
- receiving a vector comprising features extracted from an artefact;
- inputting the vector into a classification model to generate a score, the classification model being a machine learning model trained to characterize a likelihood of the file as being malicious;
- obfuscating the score by applying position-dependent noise to the generated score to result in a modified score;
- and providing the modified score to a consuming application or process.
1 more element
Dependencies are inferred from the claim text.