H All,
CISA has collaborated with the Australian Signals Directorate's Australian Cyber Security Centre (ASD's ACSC) on Engaging with Artificial Intelligence-joint guidance, led by ACSC, on how to use AI systems securely.
The guidance provides AI systems users with an overview of AI-related threats as well as steps that can help them manage AI-related risks while engaging with AI systems. The guidance covers the following AI-related threats:
1. Data poisoning
2. Input manipulation
3. Generative AI hallucinations
4. Privacy and intellectual property threats
5. Model stealing and training data exfiltration
6. Re-identification of anonymized data
Note: This guidance is primarily for users of AI systems. CISA encourages developers of AI systems to review the recently published Guidelines for Secure AI System Development (https://circle.cloudsecurityalliance.org/HigherLogic/System/DownloadDocumentFile.ashx?DocumentFileKey=b631e9c6-4c9e-4daf-ae4f-018c122146c0)
@Daniele Catteddu
@Sean Heide
------------------------------
Michael Roza CPA, CISA, CIA, CC, MBA, Exec MBA, CSA Research Fe
------------------------------