Patents by Inventor Stanislav Protasov

Stanislav Protasov 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: 20220292813
    Abstract: Disclosed herein are systems and method for classifying objects in an image using a neural network. In one exemplary aspect, the techniques described herein relate to a method including: training, with a dataset including a plurality of images, a neural network to identify objects of a set of classes, wherein the neural network includes: a shared convolutional backbone with feature extraction layers, and a plurality of heads with fully connected layers, wherein there is a respective distinct head for each of the set of classes; receiving an input image depicting at least one object from the set of classes; inputting the input image into the neural network, wherein the neural network is configured to classify the at least one object into at least one class of the set of classes; and outputting the at least one class.
    Type: Application
    Filed: February 27, 2022
    Publication date: September 15, 2022
    Inventors: Sergey Ulasen, Vasyl SHANDYBA, Alexander SNORKIN, Artem SHAPIRO, Andrey ADASCHIK, Serguei Beloussov, Stanislav PROTASOV
  • Publication number: 20220292712
    Abstract: Disclosed herein are systems and method for determining environment dimensions based on landmark detection, the method including: training, with a dataset including a plurality of images featuring an environment and labelled landmarks in the environment, a neural network to identify the labelled landmarks in an arbitrary image of the environment; receiving an input image depicting the environment; generating an input tensor based on the received input image; inputting the input tensor into the neural network, wherein the neural network is configured to generate an output tensor including a position of each identified landmark and a visibility score associated with each position; calculating a homography matrix between each position in the output tensor along a camera plane and a corresponding position in an environment plane, based on a pre-built model of the environment; and outputting an image that visually connects each landmark along the environment plane based on the homography matrix.
    Type: Application
    Filed: February 27, 2022
    Publication date: September 15, 2022
    Inventors: Sergey ULASEN, Vasyl SHANDYBA, Alexander SNORKIN, Artem SHAPIRO, Andrey ADASCHIK, Serguei BELOUSSOV, Stanislav PROTASOV
  • Publication number: 20220292817
    Abstract: Disclosed herein are systems and method for detecting small objects in an image using a neural network (NN). An exemplary method may include: receiving a first NN that is trained on a dataset including a plurality of images depicting various objects; identifying a first structure of the first NN, the first structure indicative of each layer and layer size in the first NN; determining, based on the first structure, whether the first NN can classify an object less than a threshold size in an input image; in response to determining that the first NN cannot classify the object, identifying a subset of detection layers in the first NN; generating and training a second NN that has a second structure in which the subset of detection layers are replaced by at least one layer not in the subset; and receiving, from the second NN, a classification of the object.
    Type: Application
    Filed: March 8, 2022
    Publication date: September 15, 2022
    Inventors: Sergey Ulasen, Vasyl Shandyba, Alexander Snorkin, Artem Shapiro, Andrey Adaschik, Serguei Beloussov, Stanislav Protasov
  • Patent number: 11442644
    Abstract: Aspects of the present disclosure describe methods and systems for optimized re-striping in an erasure encoded storage. In one exemplary aspect, a method may receive a request to re-stripe a plurality of data blocks arranged as a tile in the erasure encoded storage, wherein the request comprises a desired tile width. The method may identify (1) a number of data blocks in the tile and (2) a width of the tile. The method may determine a maximum number of data blocks that do not need to be rearranged when reconfiguring the tile to the desired tile width. Furthermore, the method may determine a tile reconfiguration with the desired tile width that does not rearrange the maximum number of the data blocks of the tile, and may re-stripe the tile in accordance with the tile reconfiguration.
    Type: Grant
    Filed: August 6, 2020
    Date of Patent: September 13, 2022
    Assignee: Acronis International GmbH
    Inventors: Oleg Volkov, Andrey Zaitsev, Alexey Kuznetsov, Yuri Per, Stanislav Protasov, Serguei Beloussov
  • Patent number: 11436328
    Abstract: Methods and systems for safeguarding against malware such as ransomware are described. In part, the disclosure relates to systems and methods for restoring user data and other data encrypted by malware or otherwise rendered inaccessible thereby. In one embodiment, the disclosure relates to a method of safeguarding user data. The method includes monitoring a plurality of processes executing on a computing device; detecting when a first process of the plurality of processes attempts to modify one or more parameters of a user data file; determining if first process is a trusted process or an untrusted process using one or more heuristics; and if the first process is determined to be an untrusted process, create a backup version of the user data file, wherein the backup version of the user data file is created with regard to an unchanged version the user data file.
    Type: Grant
    Filed: February 23, 2018
    Date of Patent: September 6, 2022
    Inventors: Vladimir Strogov, Nikolay Grebennikov, Serguei Beloussov, Mark Shmulevich, Stanislav Protasov, Eugene Aseev
  • Patent number: 11438349
    Abstract: Disclosed herein are systems and method for protecting an endpoint device from malware. In one aspect, an exemplary method comprises performing, by a light analysis tool of the endpoint, a light static analysis of a sample, terminating the process and notifying the user when the process is malware, performing light dynamic analysis when the process is not malware based on the light static analysis, when the process is clean based on the light dynamic analysis, enabling the process to execute, when the process is malware, terminating the process and notifying the user, and when the process is suspicious pattern, suspending the process, setting a level of trust, sending the sample to a sandbox, terminating the process and notifying the user when the process is a malware based on received final verdict, enabling the process to resume executing when the process is determined as being clean based on the final verdict.
    Type: Grant
    Filed: September 24, 2020
    Date of Patent: September 6, 2022
    Assignee: Acronis International GmbH
    Inventors: Alexey Kostyushko, Vladimir Strogov, Serguei Beloussov, Stanislav Protasov, Anastasia Pereberina, Nikolay Grebennikov
  • Publication number: 20220276936
    Abstract: Disclosed herein are systems and method for determining a backup schedule on a computer system. In one exemplary aspect, a method may comprise collecting user behavior data on the computer system. The method may comprise analyzing the user behavior data to determine an optimal time of a backup session to create backup copies of modified data stored on a volume of the computer system and determining an optimal duration of the backup session based on the analyzed user behavior. The method may comprise determining a portion of the modified data that can be saved during the backup session within the optimal duration at the optimal time of backup, and performing the backup session comprising the portion.
    Type: Application
    Filed: May 16, 2022
    Publication date: September 1, 2022
    Inventors: Alexander Tormasov, Serguei Beloussov, Stanislav Protasov
  • Patent number: 11416612
    Abstract: Disclosed are systems and methods for detecting malicious applications. The described techniques detect a first process has been launched on a computing device, and monitor at least one thread associated with the first process using one or more control points of the first process. An execution stack associated with the one or more control points of the first process is received from the first process. In response to detecting activity on the one or more control points of the first process, an indication that the execution of the first process is malicious is generated by applying a machine learning classifier to the received execution stack associated with the one or more control points of the first process.
    Type: Grant
    Filed: March 15, 2019
    Date of Patent: August 16, 2022
    Assignee: Acronis International GmbH
    Inventors: Vladimir Strogov, Serguei Beloussov, Alexey Dod, Valery Chernyakovsky, Anatoly Stupak, Sergey Ulasen, Nikolay Grebennikov, Vyacheslav Levchenko, Stanislav Protasov
  • Patent number: 11403892
    Abstract: Disclosed herein are system and method for driving organization and subsequent analysis of an autonomous vehicle. In an exemplary aspect, the system and method comprise dividing a path of a vehicle into a plurality of segments based on predetermined conditions; monitoring both behavior of the vehicle and driving conditions during each of the plurality of segments; storing the behavior and the driving conditions in a plurality of records of an immutable storage; determining whether an accident has occurred involving the vehicle; in response to determining that the accident has occurred, retrieving for the plurality of segments the behavior and the driving conditions from the immutable storage; reconstructing the path using the retrieved behavior and the driving conditions and the plurality of segments; and analyzing the reconstructed path to determine a cause of the accident.
    Type: Grant
    Filed: December 4, 2019
    Date of Patent: August 2, 2022
    Assignee: Acronis International GmbH
    Inventors: Alexander Tormasov, Serguei Beloussov, Stanislav Protasov
  • Patent number: 11403389
    Abstract: Disclosed herein are systems and method for detecting unauthorized access to computing resources for cryptomining. In one exemplary aspect, a method may detect that at least one process has been launched on a computer system. In response to the detecting, the method may collect data related to the launch of the at least one process. The method may compare the collected data with behavioral rules specifying compliant behavior on the computer system. The method may identify suspicious behavior associated with the at least one process in response to determining that the collected data does not meet the behavioral rules. The method may generate an alert indicative of the suspicious behavior. In response to identifying the suspicious behavior, the method may obtain telemetry data of the computer system, and may update the behavioral rules based on the telemetry data to improve accuracy of identifying further suspicious behavior.
    Type: Grant
    Filed: June 5, 2020
    Date of Patent: August 2, 2022
    Assignee: Acronis International GmbH
    Inventors: Vadim Karasev, Sergey Lebedev, Ravikant Tiwari, Oleg Ishanov, Evgeny A Aseev, Vladimir Strogov, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220237288
    Abstract: Disclosed herein are systems and method for inspecting archived slices for malware. In one exemplary aspect, the method comprises identifying a first slice in a plurality of slices in a backup archive, wherein the first slice is an image of user data at a first time. The method comprises scanning the first slice of the plurality of slices in the backup archive and detecting at least one infected file in the first slice. The method comprises identifying a block of the first slice that corresponds to the at least one infected file. The method comprises mounting, to a disk, a second slice of the plurality of slices. The method comprises tracking the block and determining that the at least one infected file exists on the second slice and removing the infected file from the second slice by generating a respective cured slice of the second slice.
    Type: Application
    Filed: April 11, 2022
    Publication date: July 28, 2022
    Inventors: Vladimir Strogov, Anatoly Stupak, Andrey Kulaga, Alexey Sergeev, Serguei Beloussov, Stanislav Protasov
  • Patent number: 11394738
    Abstract: Systems and methods for remediating vulnerabilities on a plurality of computing devices is disclosed herein. In one exemplary aspect, a method comprises classifying monitored data into a plurality of categories using a machine learning algorithm. For each respective data file of the monitored data, the method comprises retrieving one or more policies associated with a classified category of the respective data file and determining whether respective data file complies with the one or more policies. The method further comprises generating a compliance map based on compliance with policies for each respective data file of the monitored data, wherein the compliance map indicates vulnerabilities in the plurality of computing devices, determining whether the vulnerabilities are actionable, and in response to determining the vulnerabilities are actionable, requesting actions to be performed on the plurality of devices to remediate the vulnerabilities and non-compliance.
    Type: Grant
    Filed: January 21, 2020
    Date of Patent: July 19, 2022
    Assignee: Acronis International GmbH
    Inventors: Andrey Kulaga, Vladimir Strogov, Oleg Ishanov, Stanislav Protasov, Serguei Beloussov
  • Publication number: 20220222234
    Abstract: Disclosed herein are systems and method for multiplexing data of an underlying index. In an exemplary aspect, an index handler may: search for a data file in a plurality of data buckets associated with an index, wherein at least one respective data bucket of a plurality of data buckets is attached to a respective slot of a plurality of slots; identify, based on the searching, a first data bucket of the plurality of data buckets that comprises the data file; in response to determining that the first data bucket is not attached to any of the plurality of slots, attach the first data bucket to a first slot of the plurality of slots; and enable access to the data file via the first data bucket attached to the first slot.
    Type: Application
    Filed: March 29, 2022
    Publication date: July 14, 2022
    Inventors: Alexander Andreev, Sergey Onuchin, Hiten Gajjar, Dulitha Gunasekera, Dian Bakti, Prabhuraj Reddy, Yee Chen Lim, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220207160
    Abstract: Disclosed herein are systems and method for adjusting data protection levels based on system metadata. A method may include monitoring a computing device for a cyberattack, wherein a kernel driver of the computing device is configured to allow access to kernel control paths and hash tables in accordance with a first protection level, and detecting that the cyberattack is in progress. While the cyberattack is in progress, the method may include identifying kernel control paths and hashes of software objects that will be affected by the cyberattack, and configuring the kernel driver to disable access to the identified kernel control paths and hashes of the software objects in accordance with a second protection level, wherein the second protection level includes greater access restrictions to the computing device than the first protection level.
    Type: Application
    Filed: December 19, 2021
    Publication date: June 30, 2022
    Inventors: Nikolay Grebennikov, Candid Wüest, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220207139
    Abstract: Disclosed herein are systems and methods for preventing malicious injections. In one aspect, a method includes monitoring active processes that are running in suspended mode. For each active process being monitored, the method includes injecting a dynamic link library (DLL) into the active process to hook an application programming interface (API) of an application corresponding to the active process, wherein the DLL is injected for tracking commands for suspension and resumption of the active process. The method includes monitoring file inputs and outputs of the application for anomalies while the active process is in the suspended mode, and when a command for resuming the active process is detected using the DLL, determining, based on the monitoring, whether a malicious process is inserted into the active process. The method includes allowing the suspended process to resume execution in response to determining that no malicious process is inserted in the active process.
    Type: Application
    Filed: December 6, 2021
    Publication date: June 30, 2022
    Inventors: Vladimir Strogov, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220207136
    Abstract: Disclosed herein are systems and method for detecting usage anomalies based on environmental sensor data. A method may include: receiving a physical user input at a computing device located in an environment; determining whether the physical user input was received from an authorized user of the computing device by: retrieving environmental sensor data from at least one sensor located in the environment; identifying a window of time during which the physical user input was received; and verifying a presence of the authorized user at the environment during the window of time based on the environmental sensor data; and in response to determining that the authorized user was not present in the environment during the window of time, detecting a usage anomaly and not executing the physical user input.
    Type: Application
    Filed: December 1, 2021
    Publication date: June 30, 2022
    Inventors: Nikolay Grebennikov, Candid Wüest, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220207134
    Abstract: Disclosed herein are systems and methods for securing cloud meetings using containers. In one aspect, an exemplary system comprises, a device comprising a processor, an OS operable in a user mode and a kernel mode, and a kernel driver for performing operations while in kernel mode, the kernel driver having a kernel driver interceptor configured to: register for a process notification callback for user applications used for web-based meetings, monitor to determine when a process notification callback is received, receive a process notification callback and a command line in the callback, and analyze and transmit the command line to a service that secures the meeting, wherein the securing is performed by: configuring a container for executing the user application in an isolated virtual environment, transferring, to the container, all resources needed to run the user application, and executing the user application in the container.
    Type: Application
    Filed: December 28, 2021
    Publication date: June 30, 2022
    Inventors: Stanislav Protasov, Anton Enakiev, Alexey Kostyushko, Vladimir Strogov, Serguei Beloussov
  • Publication number: 20220210169
    Abstract: Disclosed herein are systems and method for optimizing artificial intelligence (A.I)-based malware analysis on offline endpoints in a network. In one aspect, a method includes identifying a file that has not been executed on an endpoint system and scanning the endpoint system to detect malicious behavior using a machine learning algorithm. In response to determining that the endpoint system does not exhibit malicious behavior based on the machine learning algorithm, the method includes enabling execution of the file. Subsequent to the execution of the file, the method includes rescanning the endpoint system to detect malicious behavior using the machine learning algorithm. In response to determining that the endpoint system does exhibit malicious behavior subsequent to the execution, the method includes extracting attributes of the file and retraining the machine learning algorithm using the extracted attributes to detect malicious behavior associated with the file without having to execute the file.
    Type: Application
    Filed: December 1, 2021
    Publication date: June 30, 2022
    Inventors: Nikolay Grebennikov, Candid Wüest, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220201012
    Abstract: Disclosed herein are systems and method for performing failover during a cyberattack. In one exemplary aspect, a method comprises monitoring a computing device for the cyberattack and detecting that the cyberattack is in progress. While the cyberattack is in progress, the method comprises identifying a failover device that corresponds to the computing device, hardening the failover device to prevent the cyberattack from affecting the failover device, and performing failover by switching from the computing device to the failover device.
    Type: Application
    Filed: November 8, 2021
    Publication date: June 23, 2022
    Inventors: Nikolay Grebennikov, Candid Wüest, Serguei Beloussov, Stanislav Protasov
  • Publication number: 20220200996
    Abstract: Disclosed herein are systems and methods for providing network protection for web-based conferencing services. In one aspect, an exemplary system comprises, a device comprising a processor, an operating system (OS) operable in a user mode and a kernel mode, and a kernel driver for performing operations while the OS is in kernel mode, the kernel driver configured to: monitor file operations that involve objects belonging to a web conferencing service, receive a request from an application executing in a user mode, the request being for an operation to be executed in the kernel mode, when the operation involves at least one object belonging to the web conferencing service, request for an authorization from a protection service executing in the user mode, and allow the operation to be performed only when the authorization is received from the protection service.
    Type: Application
    Filed: November 16, 2021
    Publication date: June 23, 2022
    Inventors: Vladimir Strogov, Serguei Beloussov, Stanislav Protasov