Projected vector overflow penalty as mitigation for machine learning model string stuffing
AssigneeCylance Inc.
InventorEric Glen Petersen
Life of this patent
Estimating the term…
Abstract
An artifact is received from which features are extracted and used to populate a vector. The features in the vector are then reduced using a feature reduction operation to result in a modified vector having a plurality of buckets. Features within the buckets of the modified vector above a pre-determined projected bucket clipping threshold are then identified. Using the identified features, and overflow vector is then generated. The modified vector is then input into a classification model to generate a score. This score is adjusted based on the overflow vector and can then be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.
Claims20
A computer-implemented method comprising:
- receiving an artifact;
- extracting features from the artifact and populating a vector;
- reducing features in the vector using a feature reduction operation to result in a modified vector having a plurality of buckets;
- identifying features within buckets of the modified vector above a pre-determined projected bucket clipping threshold;
- generating an overflow vector based on the identified features which characterizes a level of feature stuffing in the artifact;
- inputting the modified vector into a classification model to generate a score for the artifact, the score indicating that the artifact is benign to access, execute, or continue to execute;
- adjusting the score for the artifact based on the overflow vector, the adjusted score indicating that the artifact is malicious to access, execute, or continue to execute;
- and
- providing the adjusted score for the artifact to a consuming application or process.
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 an artifact;
- extracting features from the artifact and populating a vector;
- reducing features in the vector using a feature reduction operation to result in a modified vector having a plurality of buckets;
- identifying features within buckets of the modified vector above a pre-determined projected bucket clipping threshold;
- generating an overflow vector based on the identified features which characterizes a level of feature stuffing in the artifact;
- inputting the modified vector into a classification model to generate a score for the artifact, the score indicating that the artifact is benign to access, execute, or continue to execute;
- adjusting the score for the artifact based on the overflow vector, the adjusted score indicating that the artifact is malicious to access, execute, or continue to execute;
- and
- providing the adjusted score for the artifact to a consuming application or process.
A non-transitory computer program product storing instructions which, when executed by at least one computing device, result in operations comprising:
- receiving an artifact;
- extracting features from the artifact and populating a vector;
- reducing features in the vector using a feature reduction operation to result in a modified vector having a plurality of buckets;
- identifying features within buckets of the modified vector that are indicative of feature stuffing and which are above a pre-determined projected bucket clipping threshold;
- generating an overflow vector based on the identified features which characterizes a level of feature stuffing in the artifact;
- inputting the modified vector into a classification model to generate a score for the artifact, the score indicating that the artifact is benign to access, execute, or continue to execute;
- adjusting the score for the artifact based on the overflow vector, the adjusted score indicating that the artifact is malicious to access, execute, or continue to execute;
- and
- providing the adjusted score for the artifact to a consuming application or process.
Dependencies are inferred from the claim text.