SAFEGUARD lab

The new SAFEGUARD lab, part of the ROBUST AI program, will explore, develop and validate novel auditing theories, tools, and methodologies to monitor and audit whether AI applications adhere in terms of fairness, explainability, transparency, robustness and reliability, respect of privacy, and safety and security. SAFEGUARD Lab is a collaboration between Deloitte and the Jheronimus Academy of Data Science. The lab will have 5 PhD positions initially, to be expanded later.

For more information, visit the SAFEGUARD page on the ICAI website

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.

Interested in a research position at JADS?
Check out our vacancies