Digital Sovereignty for Collaborative AI Engineering: A Survey
Venkata Satya Sai Ajay Daliparthi, Kurt Tutschku, Victor Rigworo Kebande, Nurul Momen · IEEE Access · 2025
Collaborative AI engineering is a paradigm that enables multiple stakeholders to maintain AI pipelines by exchanging artifacts, such as data, models, and software packages. It is a cost-efficient engineering process that accelerates the development of AI applications, specifically for small and medium-sized enterprises (SMEs). However, AI artifacts are often associated with inherent intellectual property (IP) or sensitive information, which hinders collaboration due to a lack of trust among stakeholders. Digital sovereignty is viewed as an ideal state where artifact owners maintain full control over their assets, such as making key decisions regarding access, storage, and interoperability. Thus, it is postulated that implementing digital sovereignty mechanisms in multi-stakeholder information systems can address the trust gap and promote collaboration. This work addresses this gap by conducting a systematic review of the literature on digital sovereignty for collaborative AI engineering. The main contributions of this work include: i) mapping digital sovereignty definitions and requirements within the context of collaborative AI engineering, ii) identifying existing technologies and concepts for implementing sovereignty features in AI engineering, and iii) analyzing existing collaborative AI platforms such as data marketplaces, data spaces, and GAIA-X. This analysis highlights their sovereignty requirements, solutions, benefits, and implementation challenges. In addition, this work iv) identifies research gaps in data pricing, confidentiality, and interoperability, and proposes future directions to enhance digital sovereignty in collaborative AI ecosystems.