Presentation describes what security challenges automotive industry encounter with towards autonomous driving. What security threats appear and why. Who are the threat agents and what are their objectives. It presents end-to-end data path security threats based on the recent automated driving hardware architectures and propose defense-in-depth to solve approach on ECU and intra-ECU level to mitigate those threats
14. AN END-TO-END AD STACK PERSPECTIVE
IN-VEHICLE HIGH-PERFORMANCE DATA CENTER
Training Data
Set
Validation Data Set
High-Performance HW
Optimized Machine
Learning Model
OTA Update Infrastructure
AD ECU HW
Automated Driving
Middleware
AutonomousDriving
“Applications”
AutonomousDriving
“Applications”
AutonomousDriving
“Applications”
Operating System
Training
Optimization / Validation
Real-Time
Telemetry
and
Analytics
Secure,
Reliable,
Compressed
Model
Training Data Annotation
DL Model Optimizer
Real-World Simulator
Optimizer Tool
HW Optimized ML
Framework
Automated Driving
Middleware
Operating System
OTA Update Infrastructure
HD Maps
Optimized Machine
Learning Model