ETSI Releases Report on Cybersecurity for Artificial Intelligence
Tuesday, May 18, 2021 | Comments

The European Telecommunications Standards Institute (ETSI) released the ETSI GR SAI 005 report that summarizes and analyses existing and potential mitigation against threats for artificial intelligence (AI)-based systems.

Setting a baseline for a common understanding of relevant AI cybersecurity threats and mitigations will be key for widespread deployment and acceptance of AI systems and applications. The report sheds light on the available methods for securing AI-based systems by mitigating known or potential security threats identified in the recent European Union Agency for Cybersecurity (ENISA) threat landscape publication and ETSI’s GR SAI 004 problem statement report. It also addresses security capabilities, challenges and limitations when adopting mitigation for AI-based systems in certain potential use cases.

AI has been driven by the rapid progress of deep learning and its wide applications, such as image classification, object detection, speech recognition and language translation. Therefore, ETSI GR SAI 005 focuses on deep learning and explores the existing mitigating countermeasure attacks.

ETSI GR SAI 005 describes the workflow of machine-learning models where the model lifecycle includes both development and deployment stages. Based on this workflow, the report summarizes existing and potential mitigation approaches against training attacks and against inference attacks, including those from evasion, model stealing and data extraction. Mitigation approaches are summarized as model enhancement and model agnostic and then grouped by their rationales.

Due to the rapid evolvement of attack technology for AI-based systems, existing mitigations can become less effective over time, although their approaches and their rationales remain in place. In addition, most of the approaches presented stem from an academic context and make certain assumptions, which need to be considered when these approaches are applied in practice. ETSI GR SAI 005 is intended to serve as a securing AI technical reference for the planning, design, development, deployment, operation and maintenance of AI-based systems. In the future, more research work needs to be done in the area of automatic verification and validation, explainability and transparency, and novel security techniques to counter emerging AI threats, ETSI said.

Find the report here.

Would you like to comment on this story? Find our comments system below.

Post a comment
Name: *
Email: *
Title: *
Comment: *


No Comments Submitted Yet

Be the first by using the form above to submit a comment!


August 2022

7 - 10
APCO Conference and Expo 2022
Anaheim, California

More Events >

Site Navigation