The Inner Circle

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
------------------------------

It needs to be stated and understood that this is not just CISA and Australia joint guidance.

This is a joint guidance from other countries including, but not limited to:

Japan

Norway

New Zealand

Singapore

UK

I've been seeing this same document with similar attributions.  This needs to be corrected.

 #ResponsibleAI

------------------------------
Sai Honig, CCSP, CISSP


Wellington, New Zealand
------------------------------

Original Message:
Sent: Jan 23, 2024 11:34:57 PM
From: Michael Roza
Subject: Joint Publication CISA and Australia ASD _ACSC Engaging with Artificial Intelligence (AI)

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
------------------------------