公开(公告)号：US20240378484A1

公开(公告)日：2024-11-14

申请号：US18288442

申请日：2022-09-13

Applicant: Google LLC

Inventor： Walter Bogorad ,  Ronald Rong Yang ,  Alexander Troesch ,  Bavin Amenya Ondieki ,  Yousef Khaled Nassar

IPC: G06N20/00

Abstract: Aspects of the disclosure are directed to retraining an ensemble machine learning model. The ensemble model can include a base model and an overlay model. The base model can be trained on an older dataset, validated, and manually verified. The overlay model can be trained on a newer dataset and automatically validated. A combination of base model predictions and overlay model predictions, with bias towards the base model predictions, can form ensemble model predictions. A model weight for optimizing the ensemble model can determine the bias, as well as indicate that the overlay model contributes too much or too little to the ensemble model.

公开(公告)号：US20230061311A1

公开(公告)日：2023-03-02

申请号：US17776664

申请日：2020-06-25

Applicant: Google LLC

Inventor： Henry James Ludemann ,  Walter Bogorad

IPC: H04L9/40 ,  G06F21/31

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting anomalous user interface interactions. One of the methods includes receiving, for a user interface element, interaction locations that indicate where interactions with the user interface element occurred when the user interface element was provided on behalf of a first system; determining a difference between (i) a first distribution of the interaction locations for the user interface element when the user interface element was provided on behalf of the first system and (ii) a second distribution of the interaction locations for the user interface element when the user interface element was provided on behalf of a second system; classifying the first distribution of the interaction locations as anomalous in response to the difference not satisfying a condition; and preventing the first system from accessing another system to which the first system was trying to gain access.