[Rats] ETSI Specification group on Securing Artificial Intelligence
Michael Richardson <mcr+ietf@sandelman.ca> Thu, 03 October 2019 18:21 UTC
Return-Path: <mcr@sandelman.ca>
X-Original-To: rats@ietfa.amsl.com
Delivered-To: rats@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id EFAA71200E6 for <rats@ietfa.amsl.com>; Thu, 3 Oct 2019 11:21:38 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.435
X-Spam-Level: *
X-Spam-Status: No, score=1.435 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_SBL_CSS=3.335, SPF_HELO_NONE=0.001, SPF_PASS=-0.001] autolearn=no autolearn_force=no
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id vLthd6N-_B1C for <rats@ietfa.amsl.com>; Thu, 3 Oct 2019 11:21:36 -0700 (PDT)
Received: from relay.sandelman.ca (relay.cooperix.net [IPv6:2a01:7e00::f03c:91ff:feae:de77]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 64EAB1200DB for <rats@ietf.org>; Thu, 3 Oct 2019 11:21:35 -0700 (PDT)
Received: from dooku.sandelman.ca (unknown [142.169.78.79]) by relay.sandelman.ca (Postfix) with ESMTPS id A92C71F47B for <rats@ietf.org>; Thu, 3 Oct 2019 18:21:33 +0000 (UTC)
Received: by dooku.sandelman.ca (Postfix, from userid 179) id E421C54D4; Thu, 3 Oct 2019 19:22:17 +0100 (WEST)
From: Michael Richardson <mcr+ietf@sandelman.ca>
To: rats@ietf.org
X-Mailer: MH-E 8.6; nmh 1.6; GNU Emacs 24.5.1
MIME-Version: 1.0
Content-Type: multipart/signed; boundary="=-=-="; micalg="pgp-sha256"; protocol="application/pgp-signature"
Date: Thu, 03 Oct 2019 14:22:17 -0400
Message-ID: <14767.1570126937@dooku.sandelman.ca>
Archived-At: <https://mailarchive.ietf.org/arch/msg/rats/G52QFKAnCTebsUVJcwNtZ4Iwnzc>
Subject: [Rats] ETSI Specification group on Securing Artificial Intelligence
X-BeenThere: rats@ietf.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Remote Attestation Procedures <rats.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/rats>, <mailto:rats-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/rats/>
List-Post: <mailto:rats@ietf.org>
List-Help: <mailto:rats-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/rats>, <mailto:rats-request@ietf.org?subject=subscribe>
X-List-Received-Date: Thu, 03 Oct 2019 18:21:40 -0000
{via a circuitous path, this came to me. There have been use cases proposed for TEEP and RATS that relate to protecting Machine Learning algorithms. I'm wondering if there are any liasons to this ETSI ISG which might want to more clearly articulate the RAGTS use case} ---- ETSI announce the creation of a new Industry Specification Group on Securing Artificial Intelligence (ISG SAI). The group will develop technical specifications to mitigate threats arising from the deployment of AI throughout multiple ICT-related industries. This includes threats to artificial intelligence systems from both conventional sources and other AIs. The ETSI Securing Artificial Intelligence group was initiated to anticipate that autonomous mechanical and computing entities may make decisions that act against the relying parties either by design or as a result of malicious intent. The conventional cycle of networks risk analysis and countermeasure deployment represented by the Identify-Protect-Detect-Respond cycle needs to be re-assessed when an autonomous machine is involved. The intent of the ISG SAI is therefore to address 3 aspects of artificial intelligence in the standards domain: * Securing AI from attack e.g. where AI is a component in the system that needs defending * Mitigating against AI e.g. where AI is the ‘problem’ or is used to improve and enhance other more conventional attack vectors * Using AI to enhance security measures against attack from other things e.g. AI is part of the ‘solution’ or is used to improve and enhance more conventional countermeasures. The purpose of the ETSI ISG SAI is to develop the technical knowledge that acts as a baseline in ensuring that artificial intelligence is secure. Stakeholders impacted by the activity of ETSI’s group include end users, manufacturers, operators and governments. Three main activities will be undertaken and confirmed during the first meeting of the group. 1) *AI Threat Ontology *Currently, there is no common understanding of what constitutes an attack on AI and how it might be created, hosted and propagated. The work to be undertaken here will seek to define what would be considered an AI threat and how it might differ from threats to traditional systems. Hence, the AI Threat Ontology specification seeks to align terminology across the different stakeholders and multiple industries. ETSI specifications will define what is meant by these terms in the context of cyber and physical security and with a narrative that should be readily accessible to all. This threat ontology will address AI as system, attacker and defence. 2) *Securing AI Problem Statement *This specification will be modelled on the ETSI GS NFV-SEC 001 “Security Problem Statement” which has been highly influential in guiding the scope of ETSI NFV and enabling “security by design” for NFV infrastructures. It will define and prioritize potential AI threats along with recommended actions. The recommendations contained in this specification will be used to define the scope and timescales for the follow-up work. 3) *Data Supply Chain Report *Data is a critical component in the development of AI systems, both raw data, and information and feedback From other AI systems and humans in the loop. However, access to suitable data is often limited, causing a need to resort to less suitable sources of data. Compromising the integrity of data has been demonstrated to be a viable attack vector against an AI system. This report will summarize the methods currently used to source data for training AI, along with a review of existing initiatives for developing data sharing protocols and analyse requirements for standards for ensuring integrity in the shared data, information and feedback, as well as the confidentiality of these. The founding members of the new ETSI group include BT, Cadzow Communications, Huawei Technologies, NCSC and Telefónica. The first meeting of ISG SAI will be held in Sophia Antipolis on 23 October. Come and join to shape the future path for secure artificial intelligence! *Contact *Claire Boyer Mob: +33 (0)6 87 60 84 40 Email: claire.boyer@etsi.org <mailto:claire.boyer@etsi.org> -------- Weitergeleitete Nachricht -------- Betreff: [ISG_SAI] Press release: ETSI launches specification group on Securing Artificial Intelligence Datum: Wed, 2 Oct 2019 08:47:01 +0000 Von: Sonia Compans <Sonia.Compans@ETSI.ORG> Antwort an: ISG_SAI Securing Artificial Intelligence <ISG_SAI@LIST.ETSI.ORG> An: ISG_SAI@LIST.ETSI.ORG Dear SAI, We launched the press release announcing the ISG creation. Do not hesitate to forward https://www.etsi.org/newsroom/press-releases/1650-2019-10-etsi-launches-specification-group-on-securing-artificial-intelligence Sonia *Sonia Compans****–*Technical Officer *ETSI*● www.etsi.org <http://www.etsi.org/> ●_sonia.compans@etsi.org <mailto:sonia.compans@etsi.org>_ Phone: +33 (0)4 92 94 43 36 ●Mobile: +33 (0)6 67 15 58 49 Watch the new ETSI video _Cybersecurity: join the players <https://youtu.be/H7pTWOVX0dg>_ ** <https://youtu.be/H7pTWOVX0dg>** This email may contain confidential information and is intended for the use of the addressee only. Any unauthorized use may be unlawful. If you receive this email by mistake, please advise the sender immediately by using the reply facility in your email software. Thank you for your co-operation.**
- [Rats] ETSI Specification group on Securing Artif… Michael Richardson
- Re: [Rats] ETSI Specification group on Securing A… Diego R. Lopez