Building security into an AI SoC using CPU features with extensions
Marco Ciaffi (Dover Microsystems), John Min (Andes Technology)
embedded.com (April 12, 2021)
With the rapid deployment of artificial intelligence (AI), the focus of AI system on chip (SoC) design has been on building smarter, faster and cheaper devices rather than safer, trusted, and more secure. Matheny is founding director of the Center for Security and Emerging Technology at Georgetown University.
Before we look at how to build security into AI SoCs at silicon level, consider what an AI system is. It comprises three elements:
- an inference engine that processes data, makes decisions, and sends commands;
- training data and a set of weights created during the machine learning phase;
- the physical device that carries out the commands.
For example, a Nest thermostat can set a user’s preferred temperature by analyzing and learning from the user’s behavior. Eventually, it can predict that the user likes to set the temperature 10 degrees cooler at night, and the inference engine will then send a command to the thermostat to lower the temperature at the same time every day.
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |
|
Andes Technology Corp. Hot IP
Related Articles
New Articles
- When Traceability Catches What Verification Does Not
- Implementing C model integration using DPI in SystemVerilog
- Stop-For-Top IP model to replace One-Stop-Shop by 2025... and support the creation of successful Chiplet business
- Lossless Compression Efficiency of JPEG-LS, PNG, QOI and JPEG2000: A Comparative Study
- Four ways to build a CAD flow: In-house design to custom-EDA tool
Most Popular
- When Traceability Catches What Verification Does Not
- Dynamic Memory Allocation and Fragmentation in C and C++
- Implementing C model integration using DPI in SystemVerilog
- Lossless Compression Efficiency of JPEG-LS, PNG, QOI and JPEG2000: A Comparative Study
- Four ways to build a CAD flow: In-house design to custom-EDA tool