Service

AI security framework design

KPMG AI Security Services

An immense cybersecurity void

AI is being embedded into every business process and technology, but you probably don’t know whether your AI is secure. KPMG AI Security Services looks to empower organizations to assess their AI ecosystem, secure their critical models, and respond to adversarial attacks.


A survey conducted by Microsoft found that
89% of surveyed companies do not have
tools in place
to secure their AI systems

Source: Adversary Machine Learning, Redmond, USA (March 2021)


Impending regulations, such as the EU’s AI Act,
will require organizations to ensure security and
trustworthiness of their high-risk AI systems 


Today, 35% of companies reported using AI in
their business, and an additional 42% reported
they are exploring AI

Source: IBM Global Adoption Index 2022, USA (May 2022) 


Recent discoveries in the attack landscape have
demonstrated that AI systems are a major target
for attacks like poisoning, evasion, and extraction

A comprehensive AI security framework

Our AI security framework design provides security teams with a playbook to proactively assess their organizations AI systems in development and production environments; it helps to secure those systems against threats such as backdoor attacks and model inversion, and respond effectively in the event of an attack. Our AI security professionals tailor the approach to meet the requirements, platforms, and capabilities of different organizations to deliver an effective and accepted security strategy.

The value-adding outputs of an AI security framework engagement can include:

Value-adding outputs


A framework for assessing and securing AI systems, and responding to adversarial events, spread across 15 domains, including policy and procedure documents in line with requirements


Written analysis of the existing AI security policies, procedures, and AI platform configurations, including any gaps or areas for improvement


Mapping of current and in-dev AI platforms, deployments, data sources, toolkits, and architectures


Mission statement for organizational AI Security


Resource and capacity requirements, goals and metrics, reporting structures, and response plans


Consideration of upcoming regulations and frameworks


Be proactive

Stay ahead of sophisticated threats against your AI systems and models, as well as regulations requiring robust security of high-risk AI models

Empower your data-science teams to continue experimenting and transforming current processes while keeping critical systems safe

KPMG AI Security Services is powered by a new supporting technology developed out of the KPMG Studio.

KPMG AI Security Services is a leading AI security and trust service provider, developing and delivering effective security solutions for AI systems and models. Our risk-based approach provides effective prioritization to secure an organization’s most critical systems.

KPMG AI Security Services is a leading AI security and trust service provider, developing and delivering effective security solutions for AI systems and models. Our risk-based approach provides effective prioritization to secure an organization’s most critical systems.

Contact us

Jonathan Dambrot

Jonathan Dambrot

Principal, Cyber Security Services, KPMG U.S.

+1 908-361-6438
Charles A. Jacco

Charles A. Jacco

Principal, Cyber Security, KPMG US

+1 212-954-1949
Matthew P. Miller

Matthew P. Miller

Principal, Advisory, Cyber Security Services, KPMG US

+1-571-225-7842