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

arXiv: https://arxiv.org/abs/2202.09027 · HTML: https://mlsanity.com/paper/2202.09027/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2022.

## Built on by (most cited first, 22 of 22)

- [Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends](https://mlsanity.com/paper/2409.14457/) (2024)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability](https://mlsanity.com/paper/2310.17944/) (2023)
- [SoK: Blockchain-Based Decentralized AI (DeAI)](https://mlsanity.com/paper/2411.17461/) (2024)
- [Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives](https://mlsanity.com/paper/2509.08380/) (2025)
- [Combining Federated Learning and Control: A Survey](https://mlsanity.com/paper/2407.11069/) (2024)
- [A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligence](https://mlsanity.com/paper/2410.17281/) (2024)
- [Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models](https://mlsanity.com/paper/2509.22723/) (2025)
- [Confidence Calibration for Systems with Cascaded Predictive Modules](https://mlsanity.com/paper/2309.12510/) (2023)
- [Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference](https://mlsanity.com/paper/2407.19775/) (2024)
- [Ethical AI for Young Digital Citizens: A Call to Action on Privacy Governance](https://mlsanity.com/paper/2503.11947/) (2025)
- [Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2311.06255/) (2023)
- [Towards Secure and Private AI: A Framework for Decentralized Inference](https://mlsanity.com/paper/2407.19401/) (2024)
- [Optimizing Privacy-Utility Trade-off in Decentralized Learning with Generalized Correlated Noise](https://mlsanity.com/paper/2501.14644/) (2025)
- [Human-AI Interaction and User Satisfaction: Empirical Evidence from Online Reviews of AI Products](https://mlsanity.com/paper/2503.17955/) (2025)
- [Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations](https://mlsanity.com/paper/2405.06993/) (2024)
- [Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network](https://mlsanity.com/paper/2408.14298/) (2024)
- [Adversarial Federated Consensus Learning for Surface Defect Classification Under Data Heterogeneity in IIoT](https://mlsanity.com/paper/2409.15711/) (2024)
- [Personalized and Resilient Distributed Learning Through Opinion Dynamics](https://mlsanity.com/paper/2505.14081/) (2025)
- [Semi-Supervised Federated Learning via Dual Contrastive Learning and Soft Labeling for Intelligent Fault Diagnosis](https://mlsanity.com/paper/2507.14181/) (2025)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)

## Abstract (arXiv)

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.