Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learning

Abstract

Motivated by the advancing computational capacity of distributed end-user equipments (UEs), as well as the increasing concerns about sharing private data, there has been considerable recent interest in machine learning (ML) and artificial intelligence (AI) that can be processed on on distributed UEs. Specifically, in this paradigm, parts of an ML process are outsourced to multiple distributed UEs, and then the processed ML information is aggregated on a certain level at a central server, which turns a centralized ML process into a distributed one, and brings about significant benefits. However, this new distributed ML paradigm raises new risks of privacy and security issues. In this paper, we provide a survey of the emerging security and privacy risks of distributed ML from a unique perspective of information exchange levels, which are defined according to the key steps of an ML process, i.e.: i) the level of preprocessed data, ii) the level of learning models, iii) the level of extracted knowledge and, iv) the level of intermediate results. We explore and analyze the potential of threats for each information exchange level based on an overview of the current state-of-the-art attack mechanisms, and then discuss the possible defense methods against such threats. Finally, we complete the survey by providing an outlook on the challenges and possible directions for future research in this critical area.

Designing Security for the Sixth Generation: About Necessity, Concepts and Opportunities

“…In addition, methods of Artificial Intelligence will be integrated into all parts of the processing stack. As AI is another enabling technology, and of pervasive and of pivotal relevance, trusted AI (Cohen, et al, 2019), trustworthy AI (Kaur, et al, 2022) and Machine Learning (ML) (Porambage, et al, 2021) addressing the privacy and security of the systems (Ma, et al, 2022), will be a crucial issue, also in terms of the acceptance of a wide range of people in the use of 6G and AI in general. The decentralisation of resources and the associated approach of integrating intelligence into the edge is achieved by methods of federated learning, secured, for instance, by Fully Homomorphic Encryption (FHE) (Sanon, et al, 2023).…”

Over-the-Air Computation for Distributed Systems: Something Old and Something New

“…In general, distributed learning systems can be vulnerable to different types of attacks, depending on which level of information is shared among the agents in the system [13]. In this article, we focus on OtA FL with transmissions of shared training model parameters over wireless links.…”