Artificial intelligence

Convoluted layers: An artificial intelligence primer

Rapid advances in artificial intelligence (AI), along with public releases of AI products, have prompted governments, businesses and criminals to accelerate efforts to incorporate this new technology into their operations. This advice provides definitions for some of the most commonly encountered AI terms in cybersecurity and a brief typology of cyberthreats that will arise from AI.

An introduction to artificial intelligence

Artificial intelligence (AI) is an emerging technology that will play an increasingly influential role in the everyday life of Australians.

Engaging with artificial intelligence

The purpose of this paper is to provide organisations with guidance on how to use artificial intelligence (AI) systems securely. The paper summarises some important threats related to AI systems and includes cybersecurity mitigation strategies to aid organisations in engaging with AI while managing risk. It provides mitigations to assist both organisations that maintain their own AI systems and organisations that use third-party AI systems.

Guidelines for secure AI system development

This document recommends guidelines for providers of any systems that use artificial intelligence (AI), whether those systems have been created from scratch or built on top of tools and services provided by others. This document is aimed primarily at providers of AI systems who are using models hosted by an organisation, or are using external application programming interfaces (APIs).

AI Data Security

This publication provides essential data security guidance for organisations that develop and/or use AI systems, including businesses, government and critical infrastructure. It highlights the importance of data security in ensuring the accuracy and integrity of AI outcomes, and presents an in-depth examination of 3 areas of data security risks in AI systems: data supply chain, maliciously modified (poisoned) data, and data drift.

Deploying AI Systems Securely

AI security is a rapidly evolving area of research. As agencies, industry, and academia discover potential weaknesses in AI technology and techniques to exploit them, organizations will need to update their AI systems to address the changing risks, in addition to applying traditional IT best practices to AI systems.

Content Credentials: Strengthening Multimedia Integrity in the Generative AI Era

This cybersecurity information sheet discusses how Content Credentials (especially Durable ones) can be valuable to protect the provenance of media, raises awareness of the state of this solution, provides recommended practices to ensure the preservation of provenance, and discusses the importance of widespread adoption across the information ecosystem.