ETSI Releases ETSI GR SAI 006 for AI/ML Hardware Security

By Chad Cox

Associate Editor

Embedded Computing Design

April 29, 2022


ETSI Releases ETSI GR SAI 006 for AI/ML Hardware Security
Image Provided by ETSI

ETSI released a Group Report, ETSI GR SAI 006, outlining the role of hardware in the security of artificial intelligence (AI).

AI hardware delivers the platform that supports and accelerates AI-related operations. Apart from standard security requirements, the hardware used in AI and machine learning (AI/ML) applications features further security requirements to shield hardware in AI/ML specific use cases, including those in which AI/ML is used to attack generic, or specific, computing, storage, and communication hardware.

According to ETSI, ETSI GR SAI 006 gives an overview of the roles of general-purpose and specialized hardware, such as neural processors and neural networks, in enabling the security of AI. The report identifies hardware vulnerabilities and common weaknesses in AI systems and outlines the mitigations available in hardware to prevent attacks, as well as the general requirements on hardware to support the security of AI (SAI).

"AI is expected to revolutionize our wireless ecosystems, and the increased integration of AI throughout our technologies and solutions makes AI security all the more important,” says Alec Brusilovsky, the ETSI SAI Industry Specification Group Rapporteur. “It's been suggested that the best way to safeguard AI is to constantly improve its security. The research featured throughout the ETSI GR SAI 006 report reveals that our coveted level of security depends on and stems from hardware security for AI".

The report also reviews possible strategies to encourage the use of AI in the protection of hardware and provides a summary of academic and industrial experience in hardware security for AI.

View the full report here