1、Guidelines for secure AI system developmentMinisterstwoCyfryzacji03About this document This document is published by the UK National Cyber Security Centre(NCSC),the US Cybersecurity and Infrastructure Security Agency(CISA),and the following international partners:National Security Agency(NSA)Federal

2、 Bureau of Investigations(FBI)Australian Signals Directorates Australian Cyber Security Centre(ACSC)Canadian Centre for Cyber Security(CCCS)New Zealand National Cyber Security Centre(NCSC-NZ)Chiles Government CSIRT National Cyber and Information Security Agency of the Czech Republic(NUKIB)Informatio

3、n System Authority of Estonia(RIA)National Cyber Security Centre of Estonia(NCSC-EE)French Cybersecurity Agency(ANSSI)Germanys Federal Office for Information Security(BSI)Israeli National Cyber Directorate(INCD)Italian National Cybersecurity Agency(ACN)Japans National center of Incident readiness an

4、d Strategy for Cybersecurity(NISC)Japans Secretariat of Science,Technology and Innovation Policy,Cabinet Office Nigerias National Information Technology Development Agency(NITDA)Norwegian National Cyber Security Centre(NCSC-NO)Poland Ministry of Digital Affairs Polands NASK National Research Institu

5、te(NASK)Republic of Korea National Intelligence Service(NIS)Cyber Security Agency of Singapore(CSA)AcknowledgementsThe following organisations contributed to the development of these guidelines:Alan Turing Institute Anthropic Databricks Georgetown Universitys Center for Security and Emerging Technol

6、ogy Google Google DeepMind IBM Imbue Inflection Microsoft OpenAI Palantir RAND Scale AI Software Engineering Institute at Carnegie Mellon University Stanford Center for AI Safety Stanford Program on Geopolitics,Technology and GovernanceDisclaimer The information in this document is provided“as is”by