-
公开(公告)号:US12063233B2
公开(公告)日:2024-08-13
申请号:US18225957
申请日:2023-07-25
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
IPC: H04L9/40 , B60R16/023 , G06N7/01 , G06N20/00 , H04L12/40
CPC classification number: H04L63/1416 , G06N7/01 , G06N20/00 , H04L12/40 , B60R16/023 , H04L2012/40215
Abstract: A reference message determining method is used in unauthorized communication detection in an onboard network system that is executed by an information processing system including at least one memory. The onboard network system including a network and one or more electronic control units connected to the network. The method includes executing unauthorized activity detection for determining whether or not a message received from the network is an attack message. A message that could not be determined to be unauthorized is regarded as a gray message. The method also includes determining whether or not the gray message is unauthorized again at a predetermined timing. In a case where the gray message is determined to be an attack message in the unauthorized-activity-detection executing operation, a communication pattern is identified based on information relating to the gray message and information relating to the plurality of the received messages previously determined as unauthorized.
-
公开(公告)号:US11765186B2
公开(公告)日:2023-09-19
申请号:US17876204
申请日:2022-07-28
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
CPC classification number: H04L63/1416 , B60R16/0232 , G06F21/554 , H04L63/1466 , G05D1/0061 , G05D1/021
Abstract: An unauthorized activity detection method in an onboard network system. The detection method includes determining whether or not a message sent out onto the network is an attack message, saving information relating to the attack message in at least one memory in a case where the message is an attack message, identifying a communication pattern from information relating to the attack message, and determining whether or not the message matches a communication pattern. The determination of whether an attack message and determination of whether matching a communication pattern are executed on each of a plurality of messages received from the network. In the determining of whether an attack message executed on a message received after executing of determining of whether matching a communication pattern, results of the determination of whether an attack message that has already be executed are used.
-
公开(公告)号:US11757903B2
公开(公告)日:2023-09-12
申请号:US17000919
申请日:2020-08-24
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
CPC classification number: H04L63/1416 , G06N7/01 , G06N20/00 , H04L12/40 , B60R16/023 , H04L2012/40215
Abstract: A method, system, and medium used in unauthorized communication detection in an onboard network system having electronic control units connected to a network include: identifying, from information relating to an attack message on the onboard network system, a communication pattern indicating features of the attack message; determining whether a candidate reference message matches the communication pattern; and determining a reference message used as a reference in determining whether or not a message sent out onto the network is an attack message, using results of the determining of whether or not the candidate reference message matches the communication pattern identified in the identifying operation.
-
公开(公告)号:US10986105B2
公开(公告)日:2021-04-20
申请号:US16244160
申请日:2019-01-10
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
Abstract: An unauthorized activity detection method in an onboard network system. The detection method includes determining whether or not a message sent out onto the network is an attack message, saving information relating to the attack message in at least one memory in a case where the message is an attack message, identifying a communication pattern from information relating to the attack message, and determining whether or not the message matches a communication pattern. The determination of whether an attack message and determination of whether matching a communication pattern are executed on each of a plurality of messages received from the network. In the determining of whether an attack message executed on a message received after executing of determining of whether matching a communication pattern, results of the determination of whether an attack message that has already be executed are used.
-
公开(公告)号:US12244607B2
公开(公告)日:2025-03-04
申请号:US17840224
申请日:2022-06-14
Inventor: Manabu Maeda , Daisuke Kunimune
IPC: H04L9/40 , B60R16/023 , H04L67/12
Abstract: A selection method is for selecting a reference message to be used to detect unauthorized communication in an in-vehicle network system including a network and one or more electronic control units connected to the network. The reference message is used as a reference for determining whether a message sent to the network is anomalous. The selection method includes: storing candidate information regarding one or more reference message candidates each being a candidate of the reference message; selecting, based on the candidate information regarding the one or more reference message candidates stored in the storing, the selection method for selecting the reference message from among the one or more reference message candidates; and selecting the reference message from among the one or more reference message candidates using the selection method.
-
公开(公告)号:US12155677B2
公开(公告)日:2024-11-26
申请号:US16583996
申请日:2019-09-26
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
Abstract: A fraud detection method includes: determining whether a period of a message repeatedly transmitted in an in-vehicle network is anomalous; detecting whether arbitration occurs when the message is transmitted in the in-vehicle network; and determining that the message is an anomalous message, in the case where the period of the message is anomalous and no arbitration occurs when the message is transmitted in the in-vehicle network.
-
公开(公告)号:US11438350B2
公开(公告)日:2022-09-06
申请号:US17194514
申请日:2021-03-08
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
Abstract: An unauthorized activity detection method in an onboard network system. The detection method includes determining whether or not a message sent out onto the network is an attack message, saving information relating to the attack message in at least one memory in a case where the message is an attack message, identifying a communication pattern from information relating to the attack message, and determining whether or not the message matches a communication pattern. The determination of whether an attack message and determination of whether matching a communication pattern are executed on each of a plurality of messages received from the network. In the determining of whether an attack message executed on a message received after executing of determining of whether matching a communication pattern, results of the determination of whether an attack message that has already be executed are used.
-
公开(公告)号:US10791129B2
公开(公告)日:2020-09-29
申请号:US16244162
申请日:2019-01-10
Inventor: Manabu Maeda , Takeshi Kishikawa , Daisuke Kunimune
IPC: H04L29/06 , H04L12/40 , G06N20/00 , G06N7/00 , B60R16/023
Abstract: A reference message deciding method used in unauthorized communication detection. The deciding method includes: identifying, from information relating to an attack message on the onboard network system, a communication pattern indicating features related to change in data values or communication timing of an attack message; determining whether or not a message sent out onto the network matches a communication pattern identified in the identifying; and deciding a reference message used in determining whether or not the message sent out is an attack message, using determination results of the determining.
-
-
-
-
-
-
-