公开(公告)号：US20190199741A1

公开(公告)日：2019-06-27

申请号：US15852331

申请日：2017-12-22

Applicant: PAYPAL, INC.

Inventor： Benjamin Hillel Myara ,  David Tolpin

IPC: H04L29/06 ,  H04L29/08 ,  G06F17/27

CPC classification number: H04L63/1425 ,  G06F17/2785 ,  H04L67/14

Abstract: Methods and systems for creating and analyzing low-dimensional representation of webpage sequences are described. Network traffic history data associated with a particular website is retrieved and a word embedding algorithm is applied to the network traffic history data to produce a low dimensional embedding. A prediction model is created based on the low-dimensional embedding. Browsing activity on the particular website is monitored. A set of sessions in the current browsing activity is flagged based on a result of applying the prediction model to the monitored browsing activity.

公开(公告)号：US20190130254A1

公开(公告)日：2019-05-02

申请号：US15794832

申请日：2017-10-26

Applicant: Paypal, Inc.

Inventor： David Tolpin ,  Amit Batzir ,  Nofar Betzalel ,  Michael Dymshits ,  Benjamin Hillel Myara ,  Liron Ben Kimon

IPC: G06N3/04 ,  G06N3/08

Abstract: Anomalies in a data set may be difficult to detect when individual items are not gross outliers from a population average. Disclosed is an anomaly detector that includes neural networks such as an auto-encoder and a discriminator. The auto-encoder and the discriminator may be trained on a training set that does not include anomalies. During training, an auto-encoder generates an internal representation from the training set, and reconstructs the training set from the internal representation. The training continues until data loss in the reconstructed training set is below a configurable threshold. The discriminator may be trained until the internal representation is constrained to a multivariable unit normal. Once trained, the auto-encoder and discriminator identify anomalies in the evaluation set. The identified anomalies in an evaluation set may be linked to transaction, security breach or population trends, but broadly, disclosed techniques can be used to identify anomalies in any suitable population.

公开(公告)号：US10152591B2

公开(公告)日：2018-12-11

申请号：US15230315

申请日：2016-08-05

Applicant: PAYPAL, INC.

Inventor： David Tolpin ,  Shlomi Boutnaru ,  Yuri Shafet

IPC: G06F21/53 ,  G06F21/56 ,  H04L29/06

Abstract: A system for discovering programming variants. The system analyzes system calls from executing a program to generate programming code or executable for a particular OS and/or CPU that would perform the same or similar actions as the program. The code that is generated is then mutated, augmented, and/or changed to create variations of the program which still functions and/or obtains the same objectives as the original code.

公开(公告)号：US20180218261A1

公开(公告)日：2018-08-02

申请号：US15420613

申请日：2017-01-31

Applicant: PAYPAL, INC.

Inventor： Benjamin Hillel Myara ,  David Tolpin

IPC: G06N3/08 ,  H04W12/12 ,  H04L29/06 ,  G06N5/04 ,  G06Q20/40

CPC classification number: G06Q20/4016 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/084 ,  G06Q20/00 ,  H04L63/1441 ,  H04W12/00505 ,  H04W12/00508 ,  H04W12/12

Abstract: A system for predicting that a user session will be fraudulent. The system can analyze an incomplete session and determine the likelihood that the session is fraudulent or not by generating completed sessions based on the incomplete session.