-
71.发明申请IMPLEMENTING USE-DEPENDENT SECURITY SETTINGS IN A SINGLE WHITE-BOX IMPLEMENTATION 有权在单一白盒实施中实施依赖于安全的安全设置公开(公告)号：US20150312224A1
公开(公告)日：2015-10-29
申请号：US14263247
申请日：2014-04-28
Applicant: NXP B.V.
Inventor： Wil Michiels , Jan Hoogerbrugge
IPC: H04L29/06
CPC classification number: H04L63/0428 , H04L9/002 , H04L9/0631 , H04L2209/043 , H04L2209/16
Abstract: A method of enforcing security settings in a cryptographic system, including: receiving, by the cryptographic system, a first input message associated with a first security setting of a plurality of security settings; performing, by the cryptographic system, a keyed cryptographic operation mapping the first input message into a first output message, wherein the keyed cryptographic operation produces a correct output message when the cryptographic system is authorized for the first security setting, wherein each of the plurality of security settings has an associated set of input messages wherein the sets of input messages do not overlap.
Abstract translation: 一种在加密系统中实施安全设置的方法，包括：由加密系统接收与多个安全设置的第一安全设置相关联的第一输入消息; 通过加密系统执行将第一输入消息映射到第一输出消息中的密钥加密操作，其中当密码系统被授权用于第一安全设置时，密钥密码操作产生正确的输出消息，其中， 安全设置具有相关联的一组输入消息，其中输入消息组不重叠。
-
公开(公告)号：US20150312039A1
公开(公告)日：2015-10-29
申请号：US14263372
申请日：2014-04-28
Applicant: NXP B.V.
Inventor： Wil Michiels , Jan Hoogerbrugge
CPC classification number: H04L9/3231 , G06F21/14 , H04L9/0625 , H04L9/0631 , H04L2209/043 , H04L2209/16
Abstract: A method of determining a fingerprint identification of a cryptographic implementation in a cryptographic system, including: receiving, by the cryptographic system, an input message that is a fingerprint identification message; performing, by the cryptographic system, a keyed cryptographic operation mapping the fingerprint identification message into an output message that includes a fingerprint identification; and outputting the output message.
Abstract translation: 一种在密码系统中确定密码实现的指纹识别的方法，包括：密码系统接收作为指纹识别消息的输入消息; 通过加密系统执行将指纹识别消息映射到包括指纹识别的输出消息中的密钥加密操作; 并输出输出消息。
-
公开(公告)号：US20240143826A1
公开(公告)日：2024-05-02
申请号：US18051531
申请日：2022-11-01
Applicant: NXP B.V.
CPC classification number: G06F21/6227 , G06N5/04
Abstract: A method is provided for protecting a machine learning (ML) model from being copied. An input sample is provided to the ML model for an inference operation. Features from an internal layer of the ML model relating to the sample are selected. Positive gradients of the features to output logits of the ML model are selected. A summation of a product of the positive gradients and the features is computed to determine a feature contribution value. The input sample is a non-problem domain sample if the feature contribution value is less than or equal to a predetermined threshold feature contribution value. An attempt to copy the ML model is determined to be underway if a predetermined percentage of a plurality of input samples input to the ML model has a feature contribution value that is less than or equal to the predetermined threshold feature contribution value.
-
公开(公告)号：US20240126931A1
公开(公告)日：2024-04-18
申请号：US18046547
申请日：2022-10-14
Applicant: NXP B.V.
CPC classification number: G06F21/75 , G06N3/0481
Abstract: A method is provided for protecting a machine learning (ML) model from a side channel attack (SCA). A permutation is performed of weights and biases for a first layer of the ML model. The permutated weights and biases of the first layer are scaled using a scaling factor greater than zero to generate scaled and permutated weights and biases for a first plurality of nodes of the first layer. The weights for a second layer immediately following the first layer are modified to compensate for the permutation and scaling of the weights and biases of the first layer. The modified weights and biases of the first and second layers are substituted for corresponding original weights and biases of the ML model. An inference engine of the ML model is executed using the modified weights and biases of the first and second layers for an inference operation.
-
公开(公告)号：US20240004998A1
公开(公告)日：2024-01-04
申请号：US17810424
申请日：2022-07-01
Applicant: NXP B.V.
IPC: G06F21/56
CPC classification number: G06F21/56 , G06F2221/034
Abstract: A method is provided for protecting a machine learning (ML) model from a side channel attack (SCA). The method is executed by a processor in a data processing system. The method includes generating a first random bit. A first weighted sum is computed for a first connection between a node of a first layer and a node of a second layer of the ML model. The first weighted sum for the first connection is equal to a multiplication of the weight of the first connection multiplied by an input to the selected node. In the multiplication, one of the weight or the input is negated conditioned on a value of the random bit. A first output including the computed first weighted sum is provided to one or more nodes of a second layer of the plurality of layers.
-
Patent Agency Ranking
公开(公告)号：US20210133362A1
公开(公告)日：2021-05-06
申请号：US17081589
申请日：2020-10-27
Applicant: NXP B.V.
Inventor： Marcel Medwed , Tobias Schneider , Ventzislav Nikov , Jorge Miguel Ventuzelos Pereira , Rudi Verslegers , Nikita Veshchikov , Joppe Willem Bos , Jan Hoogerbrugge
Abstract: A device and methods are described that comprise at least one host application and a rich execution environment. At least one interface is operably coupled to the REE for communicating with a remote server. A security sub-system comprises a security monitoring and control circuit coupled to the REE and connectable to the remote server via the REE and the at least one interface. The security monitoring and control circuit comprises an analytics circuit configured to detect an anomaly following a compromisation of the device. The security monitoring and control circuit is arranged to treat the REE as an untrusted component and in response to a detection of a compromisation of the REE or a component in the device that is accessible by the REE by the analytics circuit, the security monitoring and control circuit is configured to re-establish a secure connection to the remote server that tunnels through the REE and at least partially removes the compromisation from the device.
-
公开(公告)号：US20200264976A1
公开(公告)日：2020-08-20
申请号：US16278246
申请日：2019-02-18
Applicant: NXP B.V.
Inventor： Jan Hoogerbrugge , Marcel Medwed , Ventzislav Nikov , Asier Goikoetxea Yanci
IPC: G06F12/0802
Abstract: A data processing system and method for protecting a memory from unauthorized accesses are provided. The data processing system includes a system bus, a memory coupled to the system bus through a memory controller, and a processing core including a cache system. The memory controller is coupled to the system bus for controlling accesses to the memory that are requested by the processing core. A memory protection circuit is coupled to the system bus and to the processing core. The memory protection circuit uses one or more memory safety violation (MSV) indicators stored in out-of-bounds areas of the memory for detecting when the processing core attempts to access an out-of-bounds area of the memory. The processing core generates an error signal, such as an interrupt, when an attempt to access the out-of-bounds area is detected. The out-of-bounds area may be an unallocated area of the memory. The MSV indicator may be written to the memory by executing a flush instruction of the cache system and may include the same number of bits as a cache line of the cache system. A data value of the MSV indicator may be a secret data value.
-
公开(公告)号：US10678474B1
公开(公告)日：2020-06-09
申请号：US16206066
申请日：2018-11-30
Applicant: NXP B.V.
Inventor： Marcel Medwed , Jan Hoogerbrugge , Ventzislav Nikov
Abstract: A computing system using low-fat pointers, including: a memory configured to be accessed by the low-fat pointers; a processing core configured to access the memory; an interrupt controller configured to receive interrupts and to communicate interrupts to processes running on the processing core; and a memory safety peripheral configured to receive a pointer request, wherein the pointer is a low-fat pointer and to verify that the pointer request is within required memory bounds.
-
79.发明授权公开(公告)号：US10599820B2
公开(公告)日：2020-03-24
申请号：US14259395
申请日：2014-04-23
Applicant: NXP B.V.
Inventor： Jan Hoogerbrugge , Phillippe Teuwen , Wil Michiels
Abstract: A method of obscuring software code including a plurality of basic blocks wherein the basic blocks have an associated identifier (ID), including: determining, by a processor, for a first basic block first predecessor basic blocks, wherein first predecessor basic blocks jump to the first basic block and the first basic block jumps to a next basic block based upon a next basic block ID; producing, by the processor, a mask value based upon the IDs of first predecessor basic blocks, wherein the mask value identifies common bits of the IDs of the first predecessor basic blocks; and inserting, by the processor, an instruction in the first basic block to determine a next basic block ID based upon the mask value and an ID of one of the first predecessor basic blocks.
-
公开(公告)号：US10412054B2
公开(公告)日：2019-09-10
申请号：US14313402
申请日：2014-06-24
Applicant: NXP B.V.
Inventor： Wil Michiels , Jan Hoogerbrugge
Abstract: A method of performing a cryptographic operation using a cryptographic implementation in a cryptographic system, including: receiving, by the cryptographic system, an identifying string value; receiving, by the cryptographic system, an input message; performing, by the cryptographic system, a keyed cryptographic operation mapping the input message into an output message wherein the output message is the correct result when the identifying string value is one of a set of binding string values, wherein the set includes a plurality of binding string values.
-
-
-
-
-
-
-
-
-
Search Results
97
records
(took 0.017 seconds)
