-
公开(公告)号：US20210406346A1
公开(公告)日：2021-12-30
申请号：US16916306
申请日：2020-06-30
Applicant: Bank of America Corporation
Inventor： WenTsong Shiue , Xianhong Zhang , Yu Fu
Abstract: Aspects of the disclosure relate to determining optimal machine learning models. A computing platform may collect, via a network, data indicative of login activity to an enterprise resource. One or more initial features indicative of the login activity may be identified. Based on the one or more initial features, an initial test dataset and a test model may be generated. Then, the test model may be deployed in a production environment. Subsequently, the computing platform may identify one or more production feature vectors. Then, the computing platform may generate, based on the one or more production feature vectors, a training dataset. Subsequently, the computing platform may perform, for the training dataset, a data quality check. Then, the computing platform may predict, by applying Bayesian optimization to the training dataset, an optimal machine learning model. Subsequently, the computing platform may apply the optimal machine learning model to detect unauthorized activity.
-
公开(公告)号：US10965675B2
公开(公告)日：2021-03-30
申请号：US15920549
申请日：2018-03-14
Applicant: Bank of America Corporation
Inventor： Xianhong Zhang , Kalyan V. Pasumarthi , Jeffrey Jacoby , Hitesh Shah , Archie Agrawal , Michael E. Toth , Yu Fu
IPC: H04L29/06
Abstract: Aspects of the disclosure relate to preventing unauthorized access to secured information systems using advanced pre-authentication techniques. A computing platform may receive, from a local traffic manager, a first enriched access request associated with a first remote computing device. Then, the computing platform may apply a pre-authentication classification model to the first enriched access request associated with the first remote computing device. Thereafter, the computing platform may determine that the first enriched access request associated with the first remote computing device is likely malicious. Then, the computing platform may generate one or more first pre-authentication response commands directing client portal server infrastructure to process the first enriched access request associated with the first remote computing device as a malicious request. Subsequently, the computing platform may send the one or more first pre-authentication response commands to the client portal server infrastructure.
-
3.发明申请公开(公告)号：US20190289007A1
公开(公告)日：2019-09-19
申请号：US15920549
申请日：2018-03-14
Applicant: Bank of America Corporation
Inventor： Xianhong Zhang , Kalyan V. Pasumarthi , Jeffrey Jacoby , Hitesh Shah , Archie Agrawal , Michael E. Toth , Yu Fu
IPC: H04L29/06
Abstract: Aspects of the disclosure relate to preventing unauthorized access to secured information systems using advanced pre-authentication techniques. A computing platform may receive, from a local traffic manager, a first enriched access request associated with a first remote computing device. Then, the computing platform may apply a pre-authentication classification model to the first enriched access request associated with the first remote computing device. Thereafter, the computing platform may determine that the first enriched access request associated with the first remote computing device is likely malicious. Then, the computing platform may generate one or more first pre-authentication response commands directing client portal server infrastructure to process the first enriched access request associated with the first remote computing device as a malicious request. Subsequently, the computing platform may send the one or more first pre-authentication response commands to the client portal server infrastructure.
-
公开(公告)号：US11531734B2
公开(公告)日：2022-12-20
申请号：US16916306
申请日：2020-06-30
Applicant: Bank of America Corporation
Inventor： WenTsong Shiue , Xianhong Zhang , Yu Fu
Abstract: Aspects of the disclosure relate to determining optimal machine learning models. A computing platform may collect, via a network, data indicative of login activity to an enterprise resource. One or more initial features indicative of the login activity may be identified. Based on the one or more initial features, an initial test dataset and a test model may be generated. Then, the test model may be deployed in a production environment. Subsequently, the computing platform may identify one or more production feature vectors. Then, the computing platform may generate, based on the one or more production feature vectors, a training dataset. Subsequently, the computing platform may perform, for the training dataset, a data quality check. Then, the computing platform may predict, by applying Bayesian optimization to the training dataset, an optimal machine learning model. Subsequently, the computing platform may apply the optimal machine learning model to detect unauthorized activity.
-
-
-
Search Results
4
records
(took 0.018 seconds)
