公开(公告)号：US20200061929A1

公开(公告)日：2020-02-27

申请号：US16109154

申请日：2018-08-22

Applicant: NXP B.V.

Inventor： NIKITA VESHCHIKOV

IPC: B29C64/40 ,  B29C64/386 ,  G06K19/07

Abstract: A method is provided for embedding an integrated circuit (IC) into a 3D-printed object. The method includes providing a filament having a material for 3D-printing an object, and an integrated circuit embedded within the filament material. The filament is used to form at least part of the 3D-printed object. A 3D-printing system is provided for implementing the method. The 3D-printing system includes a filament dispenser for storing and dispensing the 3D-printing filament. A platform provides a work surface for supporting the object as the object is being printed. A processor is provided for controlling a printing operation of the 3D-printer, and for 3D-printing the object with the filament having the ICs embedded therein. A configuration circuit is provided for configuring the IC as the IC is embedded in the 3D-printed object.

公开(公告)号：US20210019661A1

公开(公告)日：2021-01-21

申请号：US16511082

申请日：2019-07-15

Applicant: NXP B.V.

Inventor： JOPPE WILLEM BOS ,  SIMON JOHANN FRIEDBERGER ,  NIKITA VESHCHIKOV ,  CHRISTINE VAN VREDENDAAL

IPC: G06N20/20 ,  G06N3/08

Abstract: A method is provided for detecting copying of a machine learning model. In the method, the first machine learning model is divided into a plurality of portions. Intermediate outputs from a hidden layer of a selected one of the plurality of portions is compared to corresponding outputs from a second machine learning model to detect the copying. Alternately, a first seal may be generated using the plurality of inputs and the intermediate outputs from nodes of the selected portion. A second seal from a suspected copy that has been generated the same way is compared to the first seal to detect the copying. If the first and second seals are the same, then there is a high likelihood that the suspected copy is an actual copy. By using the method, only the intermediate outputs of the machine learning model outputs have to be disclosed to others, thus protecting the confidentiality of the model.

公开(公告)号：US20210004499A1

公开(公告)日：2021-01-07

申请号：US16502668

申请日：2019-07-03

Applicant: NXP B.V.

Inventor： NIKITA VESHCHIKOV ,  VENTZISLAV NIKOV

IPC: G06F21/76 ,  G06N20/10 ,  G06K9/62 ,  G06N3/08 ,  G06F21/56

Abstract: A method and data processing system are provided for detecting a malicious component in a data processing system. The malicious component may be of any type, such as a hardware trojan, malware, or ransomware. In the method, a plurality of counters is used to count events in the data processing system during operation, where each event has a counter associated therewith. A machine learning model is trained a normal pattern of behavior of the data processing system using the event counts. After training, an operation of the data processing system is monitored using the machine learning model. Current occurrences of events in the data processing system are compared to the normal pattern of behavior. If a different pattern of behavior is detected, an indication, such as a flag, of the different pattern of behavior is provided.

公开(公告)号：US20200233936A1

公开(公告)日：2020-07-23

申请号：US16250074

申请日：2019-01-17

Applicant: NXP B.V.

Inventor： NIKITA VESHCHIKOV ,  JOPPE WILLEM BOS ,  SIMON JOHANN FRIEDBERGER

IPC: G06F21/12 ,  G06N20/00

Abstract: A method is provided for detecting copying of a machine learning model. A plurality of inputs is provided to a first machine learning model. The first machine learning model provides a plurality of output values. A sequence of bits of a master input is divided into a plurality of subsets of bits. The master input may be an image. Each subset of the plurality of subsets of bits corresponds to one of the plurality of output values. An ordered sequence of the inputs is generated based on the plurality of subsets of bits. The ordered sequence of the inputs is inputted to a second machine learning model. It is then determined if output values from the second machine learning model reproduces the predetermined master input. If the predetermined master input is reproduced, the second machine learning model is a copy of the first machine learning model.

公开(公告)号：US20200012782A1

公开(公告)日：2020-01-09

申请号：US16027521

申请日：2018-07-05

Applicant: NXP B.V.

Inventor： MIROSLAV KNEZEVIC ,  NIKITA VESHCHIKOV

IPC: G06F21/54

Abstract: A method is provided for shuffling an order of a plurality of data blocks. In the method, a random number is generated, the random number corresponding to an index for a data block of the plurality of data blocks, where each data block of the plurality of data blocks has an index that uniquely identifies each data block of the plurality of data blocks. The increment function with a parameter is applied to the random number to generate a new index, the new index corresponds to a data block of the plurality of data blocks. The data block corresponding to the new index is selected as the next data block of a reordering of the plurality of data blocks. The method is iterated until the reordering of the plurality of data blocks is complete.

公开(公告)号：US20190310941A1

公开(公告)日：2019-10-10

申请号：US15945047

申请日：2018-04-04

Applicant: NXP B.V.

Inventor： NIKITA VESHCHIKOV

IPC: G06F12/0844

Abstract: A data processing system includes a processor, a cache memory, a speculative cache memory, and a control circuit. The processor is for executing instructions. The cache memory is coupled to the processor and is for storing the instructions and related data. A speculative cache is coupled to the processor and is for storing only speculative instructions and related data. The control circuit is coupled to the processor, to the cache memory, and to the speculative cache. The control circuit is for causing speculative instructions to be stored in the speculative cache in response to receiving an indication from the processor. Also, a method is provided for speculative execution in the data processing system.