Vamsi Kris Akkineni from Los Altos, CA, age 51

Resumes

Quantitative Analyst, Sustainable Energy R&D, At Google

view source

Location:

San Francisco Bay Area

Industry:

Internet

Vamsi Akkineni

view source

Us Patents

Feature Selection Using Term Frequency-Inverse Document Frequency (Tf-Idf) Model
view source
US Patent:

20210019422, Jan 21, 2021
Filed:

Jul 17, 2019
Appl. No.:

16/514042
Inventors:

- Palo Alto CA, US
Zhen MO - Sunnyvale CA, US
Vijay GANTI - Fremont CA, US
Vamsi Krishna AKKINENI - Los Gatos CA, US
Assignee:

VMware, Inc. - Palo Alto CA
International Classification:

G06F 21/57
G06N 20/00
Abstract:

A feature selection methodology is disclosed. In a computer-implemented method, the feature selection methodology automatically monitors components of a computing environment. The feature selection methodology then determines the importance of various components of the computing environment. The feature selection methodology further outputs results of the determining of the importance of the components within the computing device.

Security In A Computing Environment By Automatically Defining The Scope And Services Of Components Within The Computing Environment
view source
US Patent:

20210019577, Jan 21, 2021
Filed:

Jul 17, 2019
Appl. No.:

16/514059
Inventors:

- Palo Alto CA, US
Zhen MO - Sunnyvale CA, US
Vijay GANTI - Fremont CA, US
Vamsi Krishna AKKINENI - Los Gatos CA, US
Assignee:

VMware, Inc. - Palo Alto CA
International Classification:

G06K 9/62
G06F 9/455
G06N 20/00
G06F 17/16
Abstract:

A feature selection methodology is disclosed. In a computer-implemented method, components of a computing environment are automatically monitored, and have a feature selection analysis performed thereon. Provided the feature selection analysis determines that features of the components are well defined, a classification of the features is performed. Provided the feature selection analysis determines that features of the components are not well defined, a similarity analysis of the features is performed. Results of the feature selection methodology are generated.

Creating A Clustering Model For Evaluating A Command Line Interface (Cli) Of A Process
view source
US Patent:

20210004408, Jan 7, 2021
Filed:

Jul 3, 2019
Appl. No.:

16/502768
Inventors:

- Palo Alto CA, US
Vamsi AKKINENI - Los Gatos CA, US
International Classification:

G06F 16/906
G06F 9/455
Abstract:

Certain aspects of the present disclosure relate to methods and systems for evaluating a first command line interface (CLI) input of a process. The method comprises examining the first CLI input and selecting a first clustering model corresponding to the process, wherein the first clustering model is created based on a first clustering configuration and a first feature type combination. The method further comprises creating a first feature combination for the first CLI input based on the first feature type combination, evaluating the first CLI input using the first clustering model and the first feature combination, wherein the evaluating further comprises determining a similarity score corresponding to a similarity between the first feature combination and the one or more clusters, and determining whether or not the first CLI input corresponds to normal behavior based on the similarity score.

Event-Triggered Behavior Analysis
view source
US Patent:

20200218800, Jul 9, 2020
Filed:

Jan 8, 2019
Appl. No.:

16/242396
Inventors:

- Palo Alto CA, US
Vijay GANTI - Fremont CA, US
Zhen MO - Sunnyvale CA, US
Bin ZAN - Santa Clara CA, US
Vamsi AKKINENI - Los Gatos CA, US
International Classification:

G06F 21/55
G06F 21/53
G06F 21/56
G06K 9/62
G06N 20/00
Abstract:

Certain aspects herein provide a system and method for performing behavior analysis for a computing device by a computing system. In certain aspects, a method includes detecting an event occurring at the computing device at a first time, determining, based on the detecting, an event category of the event, and collecting first one or more behaviors associated with the determined event category occurring on the computing device based. The method also includes comparing the first one or more behaviors with a dataset indicating one or more expected behaviors of the computing device associated with the event. Upon determining that at least one of the first one or more behaviors corresponds to an unexpected behavior based on the comparing, the method further comprises taking one or more remedial actions.

Holo-Entropy Adaptive Boosting Based Anomaly Detection
view source
US Patent:

20200174867, Jun 4, 2020
Filed:

Nov 29, 2018
Appl. No.:

16/205138
Inventors:

- Palo Alto CA, US
Bin ZAN - Santa Clara CA, US
Vijay GANTI - Fremont CA, US
Vamsi AKKINENI - Los Gatos CA, US
HengJun TIAN - Sunnyvale CA, US
International Classification:

G06F 11/07
G06F 21/56
Abstract:

A computer-implemented method for determining whether data is anomalous includes generating a holo-entropy adaptive boosting model using, at least in part, a set of normal data. The holo-entropy adaptive boosting model includes a plurality of holo-entropy models and associated model weights for combining outputs of the plurality of holo-entropy models. The method further includes receiving additional data, and determining at least one of whether the additional data is normal or abnormal relative to the set of normal data or a score indicative of how abnormal the additional data is using, at least in part, the generated holo-entropy adaptive boosting model.

Method And System For Anonymizing Activity Records
view source
US Patent:

20180239918, Aug 23, 2018
Filed:

Apr 18, 2018
Appl. No.:

15/956514
Inventors:

- San Jose CA, US
Russell Alan Bruechert - Hoddesdon, GB
Roderick Duncan Stamp - Beaconsfield, GB
Arun Narasimha Swami - Cupertino CA, US
Vamsi Krishna Akkineni - Fremont CA, US
International Classification:

G06F 21/62
G06F 21/55
Abstract:

A method for processing activity records. The method includes obtaining an activity record, and generating an anonymization dictionary. Generating the anonymization dictionary includes detecting, in the activity record, a set of target entities to be anonymized, making a determination that a resource is associated with a subset of the target entities of the set of target entities, and after making the determination, assigning an anonymized identity to the subset of target entities, and generating an anonymization identifier for each target entity in the subset of target entities to obtain a set of anonymization identifiers, each including the anonymized identity. The method further includes processing the activity record using the anonymization dictionary to obtain an anonymized activity record and storing the anonymized activity record.

Method And System For Anonymizing Activity Records
view source
US Patent:

20170098093, Apr 6, 2017
Filed:

Oct 2, 2015
Appl. No.:

14/874265
Inventors:

Rajan Peng Kiat Koo - San Jose CA, US
Russell Alan Bruechert - Hoddesdon, GB
Roderick Duncan Stamp - Beaconsfield, GB
Arun Narasimha Swami - Cupertino CA, US
Vamsi Krishna Akkineni - Fremont CA, US
Assignee:

DTEX SYSTEMS LTD. - London
DTEX SYSTEMS INC. - San Jose CA
International Classification:

G06F 21/62
G06F 21/55
Abstract:

A method for processing activity records. The method includes obtaining an activity record, and generating an anonymization dictionary. Generating the anonymization dictionary includes detecting, in the activity record, a set of target entities to be anonymized, making a determination that a resource is associated with a subset of the target entities of the set of target entities, and after making the determination, assigning an anonymized identity to the subset of target entities, and generating an anonymization identifier for each target entity in the subset of target entities to obtain a set of anonymization identifiers, each including the anonymized identity. The method further includes processing the activity record using the anonymization dictionary to obtain an anonymized activity record and storing the anonymized activity record.