AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning

Alexandros Balla; Spyros Lalis

cs.DCOct 30, 2026

AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning

Authors: Alexandros Balla, Spyros Lalis

Organizations: Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong SAR, China · Department of Electrical and Computer Engineering University of Thessaly Volos, Greece

Abstract

Federated learning (FL) keeps raw data local, but most deployments still rely on a trusted coordinator for client admission, checkpoint distribution, update collection, aggregation, and rewards. This paper presents AuditFL, a contract-backed clearing layer for auditable FL in open settings. AuditFL keeps training and aggregation off chain, stores model artifacts in an assumed reliable off-chain artifact store, and records only content identifiers and economic state on chain. Clients reserve update tickets with deposits, publish update identifiers, and later claim refunds or rewards; the task coordinator publishes global checkpoints and finalizes rounds through deterministic settlement rules. The design does not remove the aggregator, but makes its on-chain round decisions attributable, replayable, auditable, and economically constrained. We implement AuditFL as both a deterministic state-machine prototype and a Solidity contract on a local Ethereum-compatible Anvil chain. On full MNIST with Dirichlet non-IID splits, 12 rounds, and up to 200 clients, AuditFL preserves the Plain FL learning trajectory while its overhead follows closed-form control-plane models. At 200 clients, the contract run issues 5,026 transactions, stores 2,413 off-chain artifacts (144.9 MiB), and consumes 829.7M EVM gas, dominated by per-client reserve and publish calls. Controlled dropout, invalid-update, and artifact-unavailability stress tests reduce inclusion nearly linearly but still finalize rounds, with final-accuracy changes remaining within a few tenths of an accuracy percentage point even under high injected failure rates.

Figures & tables

Work	Open	Commit.	Partic.	Econ.	Contract	Fault/	Main emphasis
	admit.	refs.*	bond	settle.	cost	attack focus
BlockFL [ 8 ]	$\triangle$	–	–	–	–	–	block-generation latency
Biscotti [ 10 ]	$\checkmark$	$\checkmark$	–	–	–	$\checkmark$	private/secure P2P FL
FedCoin [ 15 ]	$\triangle$	–	–	$\checkmark$	–	–	Shapley-based payments
ChainFL [ 16 ]	–	–	–	–	$\triangle$	–	on-chain model storage/aggregation
BlockFLA [ 17 ]	–	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	backdoor accountability

TABLE I: Positioning against representative blockchain-assisted, accountable, auditable, and verifiable FL work.

Fig. 1: AuditFL round workflow. Solid arrows denote control transactions and accounting state, while dashed arrows denote off-chain artifact transfers. Only identifiers and economic state enter the chain; tensors stay outside contract execution.

Object	Main effect and checks
ListingTx	Creates a task with model identifier, initial content identifier, deadlines, deposits, and immutable rules.
FundingTx	Adds tokens to the reward pool after signer, balance, and amount checks.
UpdateIntentTx	Reserves a ticket, locks a deposit, and enforces per-account caps.
UpdatePublishTx	Binds a live unrevealed ticket to an update content identifier.
GlobalUpdateTx	Finalizes the round with global identifier, included tickets, refunds, and scores; advances the round and credits entitlements.
ClaimTx	Debits an entitlement and credits the claimant balance.

TABLE II: AuditFL transaction objects.

Fig. 3: Contract execution cost on MNIST with

R=12

Fig. 4: Committed identifier bytes and off-chain artifact bytes on MNIST with

R=12

Fig. 5: Mean included updates per round under injected failures.

Fig. 6: Final test-accuracy difference relative to Plain FL under different injected failure modes. The plotted value is AuditFL under failure minus Plain FL, in accuracy percentage points.

Federated Learning

Federated learning trains shared models across data holders without requiring them to pool their raw data.

See all 992 papers

Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
Oct 28, 2026Kiranmayee Janardhan, Karthick S, Madhusmita Panda +2Federated Learning Trust-Aware Federated Learning
Responsible AI Office, Infosys Limited, Infosys Avenue, 3rd Cross, Electronic City, Hosur Road, Bengaluru – 560100, Karnataka, India
Extending FAIR Principles with Observability for Trustworthy Federated Learning
Oct 21, 2026Hangli Ge, Noboru KoshizukaTrust-Aware Federated Learning Federated Learning
Interfaculty Initiative in Information Studies; The University of Tokyo
SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)
Feb 26, 2026Shuang Liang, Yang Hua, Linshan Jiang +4Incentive Mechanisms for Federated Learning Blockchain-Based Federated Learning
Shanghai Jiao Tong University · Queen's University Belfast · Queen’s University Belfast +1

Oct 28, 2026J/K move · Enter open · S save

Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI

Kiranmayee Janardhan, Karthick S, Madhusmita Panda, Bharathi Vokkaliga Ganesh+1

Responsible AI Office, Infosys Limited, Infosys Avenue, 3rd Cross, Electronic City, Hosur Road, Bengaluru – 560100, Karnataka, India

Federated Learning Trust-Aware Federated Learning Federated Learning Aggregation

Open paper AskPDF arXiv

Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fairness assessment, explainability monitoring, and auditability. This paper proposes Governance-Aware Federated Learning (GAFL), which combines independent governance-evidence verification, temporal trust, fairness and explanation assessment, anomaly detection, policy enforcement, normalized aggregation, and tamper-evident audit logging. Client-reported governance values are authenticated, bound to their submitted model updates, and independently recomputed before aggregation. A cross-silo prototype with 10 participants was evaluated on the Adult Income dataset under honest, benign non-IID, biased-data, malicious-update, non-compliant, falsified-evidence, and mixed-threat scenarios. Four methods were compared across five random seeds: FedAvg, FedAvg with anomaly filtering, GAFL without independent verification, and complete GAFL. Complete GAFL intervened on all affected participants at the final round across the evaluated risk scenarios, including identifying 100% of falsified-evidence participants, whereas GAFL without verification identified none of the falsified-evidence participants. Final macro-F1 ranged from 0.7520 to 0.7733 across GAFL scenarios. Complete GAFL required 173.67 plus or minus 26.94 ms of governance processing per round, compared with 3.82 plus or minus 0.79 ms for FedAvg. A strict demographic-parity threshold also caused frequent interventions for honest participants, demonstrating a significant fairness-policy and utility trade-off.

Abstract

Federated Learning

Explore similar work

Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI

Extending FAIR Principles with Observability for Trustworthy Federated Learning

SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)