JPWO2020261140A5 - - Google Patents

Claims (20)

An automotive network switch,
a plurality configured to receive packets from an electronic subsystem of the vehicle over a computer network deployed in the vehicle and to transmit the packets over the computer network to other electronic subsystems of the vehicle; a port;
receive the packet from one or more of the plurality of ports; forward the packet to at least one of the plurality of ports; and transmit the packet over a network link of the computer network. a switch core configured as
one or more processors,
obtaining at least some of the packets processed by the switch core ;
analyzing the captured packets to identify anomalies in one or more of the electronic subsystems of the vehicle ;
generating a health score including a value indicative of the severity of the anomaly in a range of severity levels ; and sending, on the computer network, notification of the anomaly including the health score external to the automotive network switch. and one or more processors configured to transmit to a central processing unit . 2. The automotive network switch of claim 1, wherein in analyzing the captured packets, the one or more processors are configured to identify existing anomalies or predict impending anomalies. At least one of the electronic subsystems has a sensor, the plurality of ports are configured to receive at least a portion of the packets from the sensor, and the one or more processors 3. A motor vehicle network switch according to claim 1 or 2, configured to identify abnormal functioning of the . 4. The automotive network of any preceding claim, wherein the one or more processors are configured to identify the anomaly in response to detecting a statistically deviant pattern of attributes of the packets. switch. The statistically deviant pattern is
statistically deviant drops of packets,
statistically deviating packet rates,
5. The automotive network switch of claim 4 , having one or more of: statistically deviant delay; and statistically deviant inter-packet spacing. 6. The automotive network switch of any one of claims 1-5, wherein the one or more processors are configured to run a machine learning model configured to detect the anomaly. 7. The one or more processors of any one of claims 1-6, wherein the one or more processors are configured to count events relating to the packet and to detect the anomaly based on the counted events. Automotive network switch. at least one of said one or more processors is a machine learning (ML) accelerator separate from a switch central processing unit (CPU) or a switch graphics processing unit (GPU) located in said automotive network switch 8. A motor vehicle network switch according to any one of claims 1 to 7, comprising: The one or more processors select one or more packet streams from among the plurality of packets processed by the automotive network switch according to predefined selection criteria, and 9. A motor vehicle network switch according to any one of the preceding claims, arranged to identify the anomaly by analyzing the packet. The one or more processors (i) inspect one or more header fields of one or more of the packets; and (ii) perform deep packet inspection (DPI) on one or more of the packets. 10. The automotive network switch of claim 9, configured to select the one or more packet streams by performing one or more of applying to. 11. An automotive network switch as claimed in any preceding claim, wherein the health score comprises a numerical value quantifying the severity of the anomaly . A method for anomaly detection in a vehicle , comprising:
An automotive network switch in the vehicle receives packets from an electronic subsystem of the vehicle over a computer network deployed in the vehicle and transmits the packets over the computer network to other electronic subsystems of the vehicle. stages and
analyzing, by the automotive network switch, at least some of the packets processed by the automotive network switch to identify anomalies in one or more of the electronic subsystems of the vehicle ;
generating a health score that includes a value indicative of the severity of the anomaly in a range of severity levels ;
and C. sending, on said computer network, said anomaly notification including said health score from said automotive network switch to a central processing unit external to said automotive network switch. 13. The method of claim 12 , wherein analyzing the packets includes identifying existing anomalies or predicting impending anomalies. receiving the packet comprises receiving at least a portion of the packet from a sensor;
14. The method of claim 12 or 13 , wherein analyzing the packet comprises identifying abnormal functioning of the sensor . 15. A method according to any one of claims 12 to 14, wherein analyzing the packet comprises identifying the anomaly in response to detecting a statistically deviant pattern of attributes of the packet. 16. The method of any one of claims 12-15, wherein analyzing the packet comprises running a machine learning model configured to detect the anomaly. 17. A method according to any one of claims 12 to 16, wherein analyzing the packet comprises counting events relating to the packet and detecting the anomaly based on the counted events. . The step of parsing the packets is performed, at least in part, by a machine learning (ML) accelerator separate from a switch central processing unit (CPU) or a switch graphics processing unit (GPU) located in the automotive network switch. 18. A method according to any one of claims 12 to 17, carried out. parsing the packets selects one or more packet streams from among the plurality of packets processed by the automotive network switch according to predefined selection criteria; 19. A method according to any one of claims 12 to 18, comprising identifying the anomaly by analyzing . 20. The method of any one of claims 12-19, wherein the health score comprises a numerical value that quantifies the severity of the anomaly.