FedMark-FM: Auditable, Risk-Adjusted Data Markets for Federated Foundation-Model Adaptation

FedChronos: Federated Fine-Tuning of Time-Series Foundation Models for Privacy-Preserving Commodity Price Forecasting

FedChronos is introduced, a framework for federated parameter-efficient fine-tuning of an already pre-trained TSFM, a setting that existing federated time-series work has not addressed, since prior methods either pre-train from scratch or align prototypes rather than adapt a fixed backbone.

Regulatory-Driven Federated Learning: A Multi-Objective Approach to Compliance and Ethical AI in Financial Systems

Federated learning (FL) allows multiple institutions to train a shared model without exchanging raw data, which makes it attractive for privacy-sensitive domains such as finance. Deploying FL across jurisdictions, however, remains difficult: privacy regimes such as the General Data Protection Regulation (GDPR) in Europe and the California Consumer Privacy Act (CCPA) impose different, and sometimes conflicting, obligations on data handling. This paper proposes a regulatory-driven FL framework that treats compliance and fairness as first-class optimization objectives rather than as afterthoughts. The framework combines locally trained models with record-level differential privacy, secure aggregation of masked model updates, and a multi-objective loss that balances predictive accuracy, jurisdiction-specific compliance constraints, and group-fairness criteria, followed by a post-hoc bias audit that corrects residual disparities. We implement the complete pipeline and evaluate it on a synthetic cross-jurisdictional credit-scoring benchmark with three regions governed by GDPR-, CCPA-, and locally-styled privacy budgets, comparing against centralized learning and baseline federated averaging over five random seeds. The proposed framework keeps every region within its differential-privacy budget (ε = 1.58, 2.41, and 3.32 against caps of 2.0, 3.0, and 4.0 at δ = 10⁻⁵), raises the disparate impact ratio from 0.88 to 0.99, reduces the demographic-parity difference from 0.068 to 0.007, and attains a perfect score on an operational compliance rubric, while giving up only 0.9 percentage points of accuracy (88.2% versus 89.1%) at roughly 2.6 times the training cost. The results also surface a known tension: enforcing demographic parity increases the equalized-odds gap, quantifying the price of fairness under differential privacy in federated financial systems.

Auditable update-utility certificates for personalized federated learning

A Mathematical Framework for Balance-Aware Federated Analytics of Confidential Multi-Entity Accounting Data

Confidential ledgers cannot usually be pooled across entities, yet generic private federated learning does not preserve the identities that make accounting data meaningful. This paper develops Balance-Aware Federated Analytics (BAFA), a constrained federated framework that combines voucher-level differential privacy, debit–credit and period-continuity regularization, account-hierarchy smoothing, secure aggregation, and a one-sided balance-aware update correction. The formulation defines neighboring ledgers by replacement of one complete voucher, bounds the sensitivity of the released representation, model update, and compressed balance sketch, and composes one cached representation release and all round-level aggregate releases with a Rényi differential-privacy accountant that explicitly models the minimum number of non-colluding noise contributors. It also specifies period-complete aggregation for multi-line vouchers, derives the one-sided correction from a half-space projection, and gives first-order balance-safety, hierarchy-stability, convergence, and complexity results under non-IID data, clipping, privacy noise, and sketch error. Our experiments use PaySim, IEEE-CIS Fraud Detection, and UCI Online Retail transformed into accounting-style multi-entity ledgers. The reported points indicate that BAFA improves predictive utility and normalized balance consistency relative to private federated baselines while keeping membership-inference attack AUC near random guessing. The transformed-ledger evaluation is intended as controlled evidence; validation on native enterprise ledgers remains necessary.

Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems

Federated learning allows banks, hospitals, and other regulated organizations to train a shared model without moving raw records off their own servers, which is attractive wherever data protection law or competitive sensitivity rules out pooling data centrally. Two problems limit how far this promise can be trusted in practice. First, the parameter updates that clients exchange still leak information about local records through gradient inversion and membership inference attacks. Second, an honest averaging rule such as FedAvg has no defense against a subset of clients that submit corrupted or adversarial updates, so a small number of malicious or compromised participants can quietly steer the shared model off course. This paper presents a federated learning framework, DP-BR-FedAvg, that combines a Gaussian-mechanism differential privacy layer with a coordinate-wise trimmed-mean Byzantine-robust aggregation rule, evaluated on a simulated cross-institutional classification task resembling fraud and clinical-risk scoring. Across sixty communication rounds with twenty clients, a quarter of them Byzantine, plain FedAvg collapses on the minority class (F1-score 0.030) while the proposed framework recovers substantially more of the signal (F1-score 0.119) while bounding the privacy loss of any single client's contribution. A Byzantine-robust aggregator with no privacy layer performs best in raw accuracy, quantifying the cost privacy imposes on robustness. The results show that privacy and robustness mechanisms interact rather than simply add, and that system design for regulated, adversarial, cross-institutional settings needs to budget for that interaction.

Routed Prototype Adapters for Federated Financial Return Prediction with Frozen LLMs

Financial return prediction increasingly relies on both financial text and structured market covariates, but adapting large language models across financial institutions remains difficult because raw data cannot be centralized and clients often exhibit heterogeneous, non-stationary market signals. This paper studies data-local federated financial return prediction with a frozen LLM, aiming to share useful cross-client adaptation while preserving client-specific predictive behavior. We propose a federated routed-adapter framework in which the server maintains a pool of lightweight adapter prototypes, each client selects a personalized mixture of these prototypes through projected directional routing, and local residual adapters are learned on private client data around the selected mixture. The server then maps uploaded residual updates back to the shared prototype space through an exact least-norm decomposition for communication-efficient aggregation. The framework keeps raw financial data and client-private prediction heads local, while uploaded residuals remain model updates and should not be interpreted as a formal privacy guarantee without additional mechanisms such as secure aggregation or differential privacy. Across FNSPID, Qlib CSI300/CSI800, and Open FinLLM forecasting benchmarks, our method achieves the best overall performance, improving CSI300 RankIC from 0.082 to 0.087 over the strongest federated PEFT baseline and reducing FNSPID MAE from 0.00537 to 0.00482. These results suggest that compositional shared adaptation with local residual personalization is a practical direction for financial LLM deployment under data-local, communication-constrained, and heterogeneous federated settings.