Patents by Inventor Arunkumar Gururajan
Arunkumar Gururajan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230385409Abstract: The technology described herein identifies malicious URLs using a classifier that is both accurate and fast. Aspects of the technology are particularly well adapted for use as a real-time URL security analysis tool because the technology is able to quickly process a URL and produce a warning when a malicious URL is identified. The rapid processing speed of the technology described herein is produced, in part, by use of only a single input signal, which is the URL itself. The high accuracy produced by the technology described herein is achieved by analyzing the unstructured text on both a character-by-character level and a word-by-word level. The technology described herein uses both character-level and word-level information from the incoming URL.Type: ApplicationFiled: August 14, 2023Publication date: November 30, 2023Inventors: Arunkumar GURURAJAN, Jack Wilson STOKES, III, Farid TAJADDODIANFAR
-
Patent number: 11762990Abstract: The technology described herein identifies malicious URLs using a classifier that is both accurate and fast. Aspects of the technology are particularly well adapted for use as a real-time URL security analysis tool because the technology is able to quickly process a URL and produce a warning when a malicious URL is identified. The rapid processing speed of the technology described herein is produced, in part, by use of only a single input signal, which is the URL itself. The high accuracy produced by the technology described herein is achieved by analyzing the unstructured text on both a character-by-character level and a word-by-word level. The technology described herein uses both character-level and word-level information from the incoming URL.Type: GrantFiled: June 30, 2020Date of Patent: September 19, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Arunkumar Gururajan, Jack Wilson Stokes, III, Farid Tajaddodianfar
-
Publication number: 20220279014Abstract: The technology described herein can identify phishing URLs using transformers. The technology tokenizes useful features from the subject URL. The useful features can include the text of the URL and other data associated with the URL, such as certificate data for the subject URL, a referrer URL, an IP address, etc. The technology may build a joint Byte Pair Encoding for the features. The token encoding may be processed through a transformer, resulting in a transformer output. The transformer output, which may be described as a token embedding, may be input to a classifier to determine whether the URL is a phishing URL. Additional or improved URL training data may be generated by permuting token order, by simulating a homoglyph attack, and by simulating an a compound word attack.Type: ApplicationFiled: April 30, 2021Publication date: September 1, 2022Inventors: Jack Wilson STOKES, III, Pranav Ravindra MANERIKER, Arunkumar GURURAJAN, Diana Anca CARUTASU, Edir Vinicio GARCIA LAZO
-
Publication number: 20210312041Abstract: The technology described herein identifies malicious URLs using a classifier that is both accurate and fast. Aspects of the technology are particularly well adapted for use as a real-time URL security analysis tool because the technology is able to quickly process a URL and produce a warning when a malicious URL is identified. The rapid processing speed of the technology described herein is produced, in part, by use of only a single input signal, which is the URL itself. The high accuracy produced by the technology described herein is achieved by analyzing the unstructured text on both a character-by-character level and a word-by-word level. The technology described herein uses both character-level and word-level information from the incoming URL.Type: ApplicationFiled: June 30, 2020Publication date: October 7, 2021Inventors: Arunkumar GURURAJAN, Jack Wilson STOKES, III, Farid TAJADDODIANFAR
-
Patent number: 10839149Abstract: Automatic generation of document templates based on recognized composition element patterns in a group of clustered documents is provided. Composition elements used in documents are typically unique to a particular user or to a group of users. An automated template generation system detects composition element patterns in documents associated with a given user. Sequences of composition elements from one document are aligned with sequences of composition elements of one or more other documents. The aligned sequences are scored to generate a document distance matrix. The documents are clustered together based on the alignment scores and a document template is generated for each corresponding cluster of documents. In one or more aspects, selecting a document template and updating it results in a modified document template or, in certain cases, a new document template. The generated document templates are displayed in a user interface for selection by a user.Type: GrantFiled: November 11, 2016Date of Patent: November 17, 2020Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Arunkumar Gururajan, Mihai Aldea, Theodor J. Scott, Kamal Choudhary, Eugene Chudin, Si-Qing Chen, Daniel R. Snyder, Michelle Keslin, Jeff D. Jarrard, Sanjeev Bagaria, John Hoegger, Cynthia Guo, Tony Y. Tzeng, Jin Hee Lim
-
Patent number: 10376230Abstract: Breast density measurements are used to perform Breast Imaging Reporting and Data System (BI-RADS) classification during breast cancer screenings. The accuracy of breast density measurements can be improved by quantitatively processing digital mammographic images. For example, breast segmentation may be performed on a mammographic image to isolate the breast tissue from the background and pectoralis tissue, while a breast thickness adjustment may be performed to compensate for decreased tissue thickness near the skin line of the breast. In some instances, BI-RADS density categorization may consider the degree to which dense tissue is dispersed throughout the breast. A breast density dispersion parameter can also be obtained using quantitative techniques, thereby providing objective BI-RADS classifications that are less susceptible to human error.Type: GrantFiled: November 10, 2014Date of Patent: August 13, 2019Assignee: iCad, Inc.Inventors: Jeffrey C. Wehnes, Arunkumar Gururajan, James Monaco, Ronald Larcom, James H. Pike
-
Publication number: 20170220545Abstract: Automatic generation of document templates based on recognized composition element patterns in a group of clustered documents is provided. Composition elements used in documents are typically unique to a particular user or to a group of users. An automated template generation system detects composition element patterns in documents associated with a given user. Sequences of composition elements from one document are aligned with sequences of composition elements of one or more other documents. The aligned sequences are scored to generate a document distance matrix. The documents are clustered together based on the alignment scores and a document template is generated for each corresponding cluster of documents. In one or more aspects, selecting a document template and updating it results in a modified document template or, in certain cases, a new document template. The generated document templates are displayed in a user interface for selection by a user.Type: ApplicationFiled: November 11, 2016Publication date: August 3, 2017Applicant: MICROSOFT TECHNOLOGY LICESNING, LLCInventors: Arunkumar Gururajan, Mihai Aldea, Theodor J. Scott, Kamal Choudhary, Eugene Chudin, Si-Qing Chen, Daniel R. Snyder, Michelle Keslin, Jeff D. Jarrard, Sanjeev Bagaria, John Hoegger, Cynthia Guo, Tony Y. Tzeng, Jin Hee Lim
-
Publication number: 20170169462Abstract: A method includes receiving, at the CPE device environment data, the environment data associated with an area serviced by the CPE device. The method includes selecting a particular advertisement from a plurality of cached advertisements based on the environment data, based on information associated with the particular advertisement, and based on historical data associated with advertisements sent to a media device. The method also includes sending the particular advertisement for display.Type: ApplicationFiled: December 11, 2015Publication date: June 15, 2017Inventors: Sheldon Kent Meredith, Lauren Savage, Arunkumar Gururajan
-
Publication number: 20160256126Abstract: Breast density measurements are used to perform Breast Imaging Reporting and Data System (BI-RADS) classification during breast cancer screenings. The accuracy of breast density measurements can be improved by quantitatively processing digital mammographic images. For example, breast segmentation may be performed on a mammographic image to isolate the breast tissue from the background and pectoralis tissue, while a breast thickness adjustment may be performed to compensate for decreased tissue thickness near the skin line of the breast. In some instances, BI-RADS density categorization may consider the degree to which dense tissue is dispersed throughout the breast. A breast density dispersion parameter can also be obtained using quantitative techniques, thereby providing objective BI-RADS classifications that are less susceptible to human error.Type: ApplicationFiled: November 10, 2014Publication date: September 8, 2016Inventors: Jeffery C. Wehnes, Arunkumar Gururajan, James Monaco, Ronald Larcom, James H. Pike