Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things
Not on the map. Why?
Abstract (arXiv)
This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as continuous verification, least privilege access (LPA), data confidentiality, and behavioral analytics into the design, training, and deployment of FMs, ZTFMs can enable secure, privacy-preserving AI across distributed, heterogeneous, and potentially adversarial IoT environments. We present the first structured synthesis of ZTFMs, identifying their potential to transform conventional trust-based IoT architectures into resilient, self-defending ecosystems. Moreover, we propose a comprehensive technical framework, incorporating federated learning (FL), blockchain-based identity management, micro-segmentation, and trusted execution environments (TEEs) to support decentralized, verifiable intelligence at the network edge. In addition, we investigate emerging security threats unique to ZTFM-enabled systems and evaluate countermeasures, such as anomaly detection, adversarial training, and secure aggregation. Through this analysis, we highlight key open research challenges in terms of scalability, secure orchestration, interpretable threat attribution, and dynamic trust calibration. This survey lays a foundational roadmap for secure, intelligent, and trustworthy IoT infrastructures powered by FMs.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 66 of its 172 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
66 of 172 references.
References · 66
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
- 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
- 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
- 2018Adversarial Attack on Graph Structured Datacited by 301
- 2023Membership Inference Attacks against Language Models via Neighbourhood Comparisoncited by 258
- 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 248
38 more
- 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
- 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
- 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
- 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
- 2021Trustworthy AI: A Computational Perspectivecited by 93
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2022Decentralized Training of Foundation Models in Heterogeneous Environmentscited by 87
- 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 85
- 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
- 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
- 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 52
- 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 50
- 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
- 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
- 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 30
- 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 27
- 2024Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systemscited by 27
- 2024A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directionscited by 25
- 2020Adversarial Privacy Preserving Graph Embedding against Inference Attackcited by 21
- 2020Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applicationscited by 21
- 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 18
- 2023netFound: Principled Design for Network Foundation Modelscited by 17
- 2023Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learningcited by 14
- 2023Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systemscited by 14
- 2024Training and Serving System of Foundation Models: A Comprehensive Surveycited by 11
- 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
- 2021Intelligent Zero Trust Architecture for 5G/6G Networks: Principles, Challenges, and the Role of Machine Learning in the context of O-RANcited by 9
- 2023Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approachcited by 9
- 2023Backdoor Threats from Compromised Foundation Models to Federated Learningcited by 8
- 2025Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Modelscited by 7
- 2023OFDMA-F2L: Federated Learning With Flexible Aggregation Over an OFDMA Air Interfacecited by 6
- 2021Membership Inference Attack and Defense for Wireless Signal Classifiers with Deep Learningcited by 5
- 2023Blockchained Federated Learning for Internet of Things: A Comprehensive Surveycited by 5
- 2025Foundation Models for CPS-IoT: Opportunities and Challengescited by 5
- 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
- 2022SoK: Hardware-supported Trusted Execution Environmentscited by 4
- 2024Leveraging Foundation Models for Zero-Shot IoT Sensingcited by 4
- 2025Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trendscited by 4
50 most cited of 66 All 66 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.