US 11,971,985 B2
Adaptive detection of security threats through retraining of computer-implemented models
Lei Xu, New York, NY (US); and Jeshua Alexis Bratman, New York, NY (US)
Assigned to Abnormal Security Corporation, San Francisco, CA (US)
Filed by Abnormal Security Corporation, San Francisco, CA (US)
Filed on Jul. 22, 2022, as Appl. No. 17/871,765.
Claims priority of provisional application 63/225,021, filed on Jul. 23, 2021.
Prior Publication US 2023/0039382 A1, Feb. 9, 2023
Int. Cl. G06F 21/55 (2013.01)
CPC G06F 21/554 (2013.01) [G06F 2221/031 (2013.01)] 34 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor configured to:
receive an indication that an existing natural language processing model, trained to classify textual content, should be retrained;
generate a set comprising a plurality of training samples, wherein the set includes at least one synthetic training sample constructed using one or more linguistic hints, comprising at least one keyword of phrase, about a particular novel attack for which malicious textual communications associated with the novel attack, when processed by the existing natural language processing model, are erroneously classified as benign textual communications;
retrain the existing natural language processing model at least in part by using the set of generated training samples; and
use the retrained model to determine a likelihood that a received communication transmitted by a sender to a recipient poses a risk; and
a memory coupled to the processor and configured to provide the processor with instructions.