Attack categorization based on machine learning feature contribution
AssigneeImperva, Inc.
InventorsOri Nakar, Nadav Avital, Aiah Lerner
Life of this patent
Estimating the term…
Abstract
According to some embodiments of the disclosure, a method includes receiving an electronic communication directed to a data resource, determining, by a machine learning (ML) web application firewall (WAF), an attack probability of the electronic communication based on a plurality of features, wherein subsets of the plurality of features are arranged in a plurality of feature groups, adjusting the attack probability based on respective feature weights of the plurality of feature groups.
Claims20
A method comprising:
- receiving an electronic communication directed to a data resource;
- determining, by a machine learning (ML) web application firewall (WAF), an attack probability of the electronic communication based on a plurality of features, wherein subsets of the plurality of features are arranged in a plurality of feature groups;
- and
- adjusting, by a processing device, the attack probability based on respective feature weights of the plurality of feature groups.
A system comprising:
- a memory to store instructions associated with a machine learning (ML) web application firewall (WAF);
- and
- a processing device operatively coupled to the memory, the processing device to:
- receive an electronic communication directed to a data resource;
- determine an attack probability of the electronic communication based on a plurality of features, wherein subsets of the plurality of features are arranged in a plurality of feature groups;
- and
- adjust the attack probability based on respective feature weights of the plurality of feature groups.
A non-transitory computer-readable medium having instructions stored thereon which, when executed by a processing device, cause the processing device to:
- receive an electronic communication directed to a data resource;
- determine, by a machine learning (ML) web application firewall (WAF), an attack probability of the electronic communication based on a plurality of features, wherein subsets of the plurality of features are arranged in a plurality of feature groups;
- and
- adjust, by the processing device, the attack probability based on respective feature weights of the plurality of feature groups.
Dependencies are inferred from the claim text.