Automotive Security through New Communication Lockdown
System Features
Scalability of the processing system and soft
processor instantiations or programmable
accelerators
implemented
in
the
programmable logic can be applied where
required.
The Zynq MP SoC architecture (Figure 5)
includes a high bandwidth interconnect
between
the
Processing
System,
Programmable Logic allows for tight
integration and flexible partitioning
between both hardware and software.
Extending this compute capability, is the
focus on Machine Learning and AI Engines 11 .
Optimized resource and power efficient
neural networks can be implemented in the
Programmable Logic to augment compute in
Automotive solutions 12 and other
applications and markets.
Optimization of algorithms running on the
processing system can be achieved by
offloading and accelerating the algorithms
using the inherent parallelism of the
programmable logic fabric while providing
the processing power scalability and
flexibility essential for these programmable
platforms across the Zynq SOC device family.
Future Direction
The
Communication
Lockdown
methodology as described in this article
extends beyond the automotive industry
and is applicable to any kind of closed
system. This includes but is not limited to
Industry 4.0
Smart-grid applications
Critical infrastructure
Medical devices.
In addition, GuardKnox is an active member
of the ISO/SAE joint working group, ISO-
TC22-SC32-WG11. This working group’s
mission is to create a new standard, ISO-SAE
21434: Road vehicles – Cybersecurity
Engineering 13 .
Figure 5: Zynq US+ MPSoC Partitioning: Processing System
and Programable Logic
11
Xilinx AI Engines and Their Applications https://www.xilinx.com/support/documentation/white_papers/wp506-ai-engine.pdf
12
Power efficient neural networks Augmenting compute in Automotive solutions:
https://www.itu.int/en/journal/001/Documents/itu2017-2.pdf
13
Goldberg, Jillian (2018, 04) Setting the Standard for Automotive Cybersecurity https://blog.guardknox.com/setting-standard-
automotive-cyber-security
- 67 -
March 2019