Safeguard Lab

Safeguard Lab

A collaboration between Deloitte and the Jheronimus Academy of Scientific Data Science.

Sint Janssingel 92, 5211 DA 's-Hertogenbosch

The research of the SAFEGUARD Lab is focused on developing and validating new auditing theories, tools, and methodologies to ensure that AI-enabled enterprise systems and applications have a high degree of integrity. SAFEGUARD Lab is a collaboration between Deloitte and the Jheronimus Academy of Scientific Data Science.

The next generation of enterprise applications is quickly becoming AI-enabled, providing novel functionalities with unprecedented levels of automation and intelligence. As we recover, reopen, and rebuild, it is time to rethink the importance of trust. At no time has it been more tested or valued in leaders and each other. Trust is the basis for connection. Trust is all-encompassing: physical, emotional, digital, financial, and ethical. A nice-to-have is now a must-have; a principle is now a catalyst; a value is now invaluable.

Trust distinguishes and elevates sociality and business. Therefore, trust should be at the forefront of AI’s planning, strategy, and purpose. Consequently, we need new approaches to render AI-enabled enterprise systems and applications trustworthy, meaning they should fulfill the following six requirements: (1) fair, (2) explainable and transparent, (3) responsible and auditable, (4) robust and reliable, (5) respectful of privacy and (6) safe and secure.  SAFEGUARD aims at realizing systems that adhere to these requirements.

“Explore, develop and validate novel auditing theories, tools, and methodologies that will be able to monitor and audit whether AI applications adhere in terms of fairness (no bias), explainability, transparency (easy to explain), robustness and reliability (delivering same results under various execution environments), respect of privacy (respecting GDPR), and safety and security (with no vulnerabilities).”

The research at the SAFEGUARD Lab is focused on several different directions. These include: developing a theoretical framework and prototypical tool for assessing bias and application smell metrics and exploring a socio-technical approach to explainability and transparency. Additionally, the SAFEGUARD lab focuses on creating a toolsuite and methodology for ensuring responsibility and accountability through internal audits, developing prototypes, and a methodology for ensuring robustness and reliability. Lastly, the lab will focus on creating an experimental toolchain with machine-learning enabled and continuous testing techniques for testing AI software components as part of a DevOps pipeline.

Sustainable Development Goals

Research projects

Fairness of AI software systems. Aims to develop methods and techniques to support audit of AI software when detecting and mitigating bias.

Audits for explainability and transparency for AI software. Aims to improve assessment of explainability and transparency of business/government decision-making based on AI.

Auditing responsibility and accountability of AI software systems. Aims to find and implement best path strategies to assess responsible and accountable AI software systems.

Auditing framework and tool for robust and reliable AI software development. Aims to develop methods to dynamically check robustness and reliability of AI pipelines, some of which are partly realized with quantum infrastructures.

Testing AI software. Aims to develop security by design using generative adversarial learning.


Willem-Jan van den Heuvel
Eric Postma

PHD Students

Willem-Jan van den Heuvel
Eric Postma


Deloitte will provide requirements for developing the framework, resources for a qualitative study, and the data to test the future product. JADS Tilburg University will provide knowledge and expertise concerning financial/economic, continuous and interactive auditing, and psychological and legal aspects. JADS Eindhoven University of Technology will bring its expertise on AI/ML in general and automatic (white/black/regression) DevOps-style testing and test case generation in particular.


  • Deloitte

  • JADS Tilburg University
Jheronimus Academy of Data Science (JADS)

Stay in the loop

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.