Patents by Inventor Mahdi Azarafrooz
Mahdi Azarafrooz 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).
-
Patent number: 11797826Abstract: A system is provided for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.Type: GrantFiled: December 18, 2020Date of Patent: October 24, 2023Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Patent number: 11283818Abstract: A system is provided for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: GrantFiled: April 28, 2020Date of Patent: March 22, 2022Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Michael Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Thomas Wojnowicz, Derek A. Soeder, David N. Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Patent number: 11188646Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The at least one memory may include program code that provides operations when executed by the at least one processor. The operations may include: training, based on a training data, a machine learning model to enable the machine learning model to determine whether at least one container file includes at least one file rendering the at least one container file malicious; and providing the trained machine learning model to enable the determination of whether the at least one container file includes at least one file rendering the at least one container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: GrantFiled: October 24, 2019Date of Patent: November 30, 2021Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Publication number: 20210256350Abstract: A system is provided for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.Type: ApplicationFiled: December 18, 2020Publication date: August 19, 2021Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Patent number: 11074494Abstract: In one respect, there is provided a system for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.Type: GrantFiled: November 7, 2016Date of Patent: July 27, 2021Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Patent number: 10922604Abstract: In one respect, there is provided a system for training a neural network adapted for classifying one or more instruction sequences. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: training, based at least on training data, a machine learning model to detect one or more predetermined interdependencies amongst a plurality of tokens in the training data; and providing the trained machine learning model to enable classification of one or more instruction sequences. Related methods and articles of manufacture, including computer program products, are also provided.Type: GrantFiled: November 7, 2016Date of Patent: February 16, 2021Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Publication number: 20200259850Abstract: A system is provided for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: ApplicationFiled: April 28, 2020Publication date: August 13, 2020Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Michael Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Thomas Wojnowicz, Derek A. Soeder, David N. Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Patent number: 10664597Abstract: Identifying shellcode in a sequence of instructions by identifying a first instruction, the first instruction identifying a first bound of a sequence of instructions, identifying a second instruction, the second instruction identifying a second bound of the sequence of instructions, and generating a distribution for the sequence of instructions, bounded by the first instruction and the second instructions, the distribution indicative of whether the sequence of instructions is likely to include shellcode.Type: GrantFiled: July 10, 2019Date of Patent: May 26, 2020Assignee: Cylance Inc.Inventors: Mahdi Azarafrooz, Derek A. Soeder
-
Patent number: 10637874Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: GrantFiled: November 7, 2016Date of Patent: April 28, 2020Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andrew Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Publication number: 20200057853Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The at least one memory may include program code that provides operations when executed by the at least one processor. The operations may include: training, based on a training data, a machine learning model to enable the machine learning model to determine whether at least one container file includes at least one file rendering the at least one container file malicious; and providing the trained machine learning model to enable the determination of whether the at least one container file includes at least one file rendering the at least one container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: ApplicationFiled: October 24, 2019Publication date: February 20, 2020Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Patent number: 10503901Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The at least one memory may include program code that provides operations when executed by the at least one processor. The operations may include: training, based on a training data, a machine learning model to enable the machine learning model to determine whether at least one container file includes at least one file rendering the at least one container file malicious; and providing the trained machine learning model to enable the determination of whether the at least one container file includes at least one file rendering the at least one container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: GrantFiled: November 7, 2016Date of Patent: December 10, 2019Assignee: Cylance Inc.Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andy Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Patent number: 10482248Abstract: Identifying shellcode in a sequence of instructions by identifying a first instruction, the first instruction identifying a first bound of a sequence of instructions, identifying a second instruction, the second instruction identifying a second bound of the sequence of instructions, and generating a distribution for the sequence of instructions, bounded by the first instruction and the second instructions, the distribution indicative of whether the sequence of instructions is likely to include shellcode.Type: GrantFiled: November 7, 2017Date of Patent: November 19, 2019Assignee: Cylance Inc.Inventors: Mahdi Azarafrooz, Derek A. Soeder
-
Publication number: 20190332772Abstract: Identifying shellcode in a sequence of instructions by identifying a first instruction, the first instruction identifying a first bound of a sequence of instructions, identifying a second instruction, the second instruction identifying a second bound of the sequence of instructions, and generating a distribution for the sequence of instructions, bounded by the first instruction and the second instructions, the distribution indicative of whether the sequence of instructions is likely to include shellcode.Type: ApplicationFiled: July 10, 2019Publication date: October 31, 2019Inventors: Mahdi Azarafrooz, Derek A. Soeder
-
Publication number: 20180129807Abstract: Identifying shellcode in a sequence of instructions by identifying a first instruction, the first instruction identifying a first bound of a sequence of instructions, identifying a second instruction, the second instruction identifying a second bound of the sequence of instructions, and generating a distribution for the sequence of instructions, bounded by the first instruction and the second instructions, the distribution indicative of whether the sequence of instructions is likely to include shellcode.Type: ApplicationFiled: November 7, 2017Publication date: May 10, 2018Inventors: Mahdi Azarafrooz, Derek A. Soeder
-
Publication number: 20180075348Abstract: In one respect, there is provided a system for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.Type: ApplicationFiled: November 7, 2016Publication date: March 15, 2018Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andrew Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Publication number: 20180075349Abstract: In one respect, there is provided a system for training a neural network adapted for classifying one or more instruction sequences. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: training, based at least on training data, a machine learning model to detect one or more predetermined interdependencies amongst a plurality of tokens in the training data; and providing the trained machine learning model to enable classification of one or more instruction sequences. Related methods and articles of manufacture, including computer program products, are also provided.Type: ApplicationFiled: November 7, 2016Publication date: March 15, 2018Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andrew Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Eric Petersen, Ming Jin, Ryan Permeh
-
Publication number: 20180063169Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: ApplicationFiled: November 7, 2016Publication date: March 1, 2018Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andrew Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh
-
Publication number: 20180060580Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The at least one memory may include program code that provides operations when executed by the at least one processor. The operations may include: training, based on a training data, a machine learning model to enable the machine learning model to determine whether at least one container file includes at least one file rendering the at least one container file malicious; and providing the trained machine learning model to enable the determination of whether the at least one container file includes at least one file rendering the at least one container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.Type: ApplicationFiled: November 7, 2016Publication date: March 1, 2018Inventors: Xuan Zhao, Matthew Wolff, John Brock, Brian Wallace, Andrew Wortman, Jian Luan, Mahdi Azarafrooz, Andrew Davis, Michael Wojnowicz, Derek Soeder, David Beveridge, Yaroslav Oliinyk, Ryan Permeh