Extending FAIR Principles with Observability for Trustworthy Federated Learning

Hangli Ge; Noboru Koshizuka

cs.LGOct 21, 2026

Extending FAIR Principles with Observability for Trustworthy Federated Learning

Authors: Hangli Ge, Noboru Koshizuka

Organizations: Interfaculty Initiative in Information Studies; The University of Tokyo

Abstract

Federated learning (FL) keeps data at its source, but locality alone does not make a federation trustworthy. Without sufficient observability, an aggregator cannot determine whether the client service was healthy, the local data pipeline was trustworthy, or contractual constraints were properly monitored during training. We take the position that trustworthy FL needs an evidence plane in addition to its model-update process. Each participant continuously summarizes local infrastructure, data into minimal, signed trust evidence associated with each FL round, while raw data, logs remain local. A local TinyLLM may assist in interpreting observability signals, deriving contextual evidence, and providing natural-language explanations to operators. We instantiate this vision through FAIR-O, an observability extension of FAIR principle. Rather than benchmarking FL accuracy, a three-level trust model has been proposed and a two-participant Python prototype demonstrates evidence generation and trust assessment. We further discuss future integration of FAIR-O Trust Evidence into participant selection, evidence weighting, and federated aggregation.

Figures & tables

Fig. 1: Overview of the FAIR-O observability architecture for trustworthy federated learning. Each FL data provider locally observes infrastructure, data, and trust-policy conditions. An optional participant-side TinyLLM supports local querying and explanation, while deterministic mechanisms generate minimal and signed FAIR-O evidence. The FAIR-O Evidence Plane manages this evidence at the Data Space layer and provides trust information to support federated-learning decisions without exposing raw data or operational telemetry.

Fig. 2: Participant A’s view of Participant B’s signed Trust Evidence

Fig. 3: Participant-A dashboard case, showing the federation overview and the FAIR-O scores of data assets owned by Participant B. Participant A can inspect participant-level trust evidence and asset-level observability scores without revealing raw data.

Fig. 4: Dashboard output for the two-participant UCI SECOM experiment. Participant A contains 940 records with a 4.5% source missing ratio. Participant B contains 313 records; controlled degradation increases its missing ratio to 14.1%, flips 16 labels, and adds feature noise with standard deviation 0.25. The dashboard compares sample-count-weighted FedAvg with models trained only by A or B and shows the FedAvg learning trajectory over 30 rounds.

Trust-Aware Federated Learning

See all 10 papers

End-to-End Verifiable and Robust Federated Learning
Sep 14, 2026Doryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini +2Federated Learning Aggregation Byzantine-Robust Federated Learning
AIT Austrian Institute of Technology · Vienna, Austria · Department of Computer Engineering +2
FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks
Jun 26, 2026Emmanuel Rassou, Tomas GonzalezHierarchical Federated Learning Federated Learning Aggregation
School of Engineering and Applied Sciences (SEAS) Harvard Cambridge, MA, USA
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges
Jun 15, 2026Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange +1Explainable Artificial Intelligence Privacy-Preserving ML
Department of Information Engineering, University of Pisa, Largo Lucio Lazzarino 1, Pisa, 56122, Italy

Sep 14, 2026J/K move · Enter open · S save

End-to-End Verifiable and Robust Federated Learning

Doryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini, José L. Hernández-Ramos+1

AIT Austrian Institute of Technology · Vienna, Austria · Department of Computer Engineering+2

Federated Learning Aggregation Byzantine-Robust Federated Learning Federated Learning

Open paper AskPDF arXiv

Federated learning enables multiple parties to train a shared model without centralizing raw data with the help of an aggregator, but introduces integrity risks once participants or infrastructure are not fully trustworthy. Two requirements are particularly important: robustness to poisoned or Byzantine client updates, and verifiability of the aggregator so that clients or third parties can audit the reported aggregation without learning individual updates. Existing work has largely treated these goals separately, and efficient public verifiability for robust, outlier-excluding aggregation remains limited. We present a verifiable federated learning protocol that makes a robust aggregation pipeline publicly auditable. Our design combines cryptographic commitments with non-interactive zero-knowledge proofs to certify both (i) cosine-similarity-based outlier exclusion and (ii) aggregation over the selected set, without revealing individual client updates to verifiers. In experiments under representative poisoning attacks, our method maintains high accuracy, with an average accuracy loss below 4% across the evaluated configurations, while keeping verification overhead practical: proof artifacts can be generated and verified within minutes at the scale studied. In summary, our results show that robust outlier exclusion and public verifiability can be jointly achieved in a federated learning setting.

Abstract

Trust-Aware Federated Learning

Explore similar work

End-to-End Verifiable and Robust Federated Learning

FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks

Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges