BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
arXiv cs.AIarXiv:2605.17508v2 Announce Type: replace-cross
Abstract: Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under non-IID data distributions, SFL often suffers from biased optimization and unstable convergence, while existing solutions largely adapt techniques from conventional federated learning. In this work, we observe that the split architecture of SFL inherently alters how client information is represented and coordinated, opening opportunities for bias compensation beyond parameter-level aggregation. Based on this insight, we propose BESplit, an architecture-aware framework that exploits the intrinsic structure of SFL to mitigate non-IID effects. First, to prevent biased local data from dominating global updates, we introduce Evidential Aggregation (EA) to perform fine-grained reweighting of client contributions based on evidential uncertainty. Second, to further reduce distributional skew, we develop Bias-Compensated Collaboration (BCC) to align split-layer representations by pairing complementary clients. Finally, Dual-Teacher Distillation (DTD) is incorporated to synchronize knowledge between decoupled client and server models, enabling independent local inference. Extensive experiments on five benchmark datasets demonstrate that BESplit consistently outperforms state-of-the-art methods in accuracy, convergence stability, and computational efficiency under diverse non-IID settings.
Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Identity-Gated Participation against Sybil Attacks
arXiv cs.AIarXiv:2602.02629v2 Announce Type: replace-cross
Abstract: Federated learning allows hospitals to train a shared clinical model without exchanging patient records, but its aggregation assumes that each participant is a distinct institution. In an open federation, an adversary can register many fake identities (a Sybil attack) and outweigh honest hospitals. Byzantine-robust aggregation mitigates such attacks only while the adversary is a minority. We ask whether binding participation to accountable institutional identity closes that gap, and at what cost. We present TBFL, a framework in which an accountable authority issues Verifiable Credentials to the Decentralized Identifiers of hospitals, and a smart-contract registry on a peer-to-peer ledger admits model updates only from credentialed senders. We evaluated a prototype on in-hospital mortality prediction with MIMIC-IV records split across simulated hospitals, comparing the identity gate with federated averaging, three robust aggregators, norm clipping, and a similarity-based defense. Robust aggregators held against a Sybil minority, and norm clipping only against random vectors; all failed when half the participants were Sybils trained on real records with flipped labels. The similarity-based defense stopped mutually similar Sybils but yielded to perturbed ones. The gate rejected all unauthorized submissions and maintained attack-free performance for every strategy up to 60% Sybils. It did not stop credentialed hospitals that flipped their own labels, whereas the gate followed by the coordinate-wise median withstood both. On a local node, on-chain checks added about 1% to training time; fees made training impractical on a public mainnet but affordable on a rollup. Identity gating complements robust aggregation rather than replacing it.
Comparative study of global pooling for pre-departure ship fuel consumption prediction: Advantages over per-ship and adaptation-based approaches
arXiv cs.AIarXiv:2611.03015v1 Announce Type: cross
Abstract: Most fuel oil consumption (FOC) models for voyage planning are per-ship models and thus generalize poorly beyond each vessel's records. Transfer and federated learning have been reported to perform better, but under different protocols that often use inputs unavailable before departure or random data splits. It therefore remains unclear which approach performs best. In this study, we compare 11 per-ship, adaptation-based, and global methods on 21 vessels. To prevent leakage, all methods receive identical inputs known or forecast before departure, excluding engine RPM and shaft power, and are tested on intact voyage legs after all training records of each vessel. Global pooling, in which one model describes each vessel by its ship identity and seven ship specifications, performs best overall in every setting examined. For in-fleet vessels, Global LightGBM reaches an overall MAPE of 8.92%, against 11.14% for Per-Ship LightGBM, and outperforms every per-ship and adaptation-based model. Global models of five architectures, including a Transformer, all outperform the per-ship and federated models. Fine-tuning a global model for each vessel, even by low-rank adaptation of the Transformer, adds no accuracy. Without any records of a vessel, the global model reaches a median MAPE of 11.20% and outperforms a per-ship model trained on that vessel's records for 14 of 21 vessels. Adding its first records to the pooled data is as accurate as vessel-specific adaptation. Ship identity and specifications are largely interchangeable for in-fleet vessels, but only the specifications support zero-shot prediction. Its error grows as a vessel's specifications differ from the fleet's. Per-ship models and vessel-specific adaptation are therefore unnecessary under fair comparison. One global model can serve a whole fleet, including newly delivered vessels with similar specifications.
MultiMental-IAS: A Multimodal Driver Mental State Analysis Dataset for Context-Aware Non-IID Evaluation
arXiv cs.AIarXiv:2611.02790v1 Announce Type: cross
Abstract: Robust driver-state modelling requires synchronized physiological, behavioural, and contextual signals, yet existing open resources typically target a single cognitive state, omit continuous vehicle context, or do not define evaluation protocols that expose inter-subject heterogeneity. We present Multimental-IAS, a multimodal driver mental-state dataset collected in a cockpit-in-the-loop simulation built on CARLA. It contains vehicle telemetry with scenario-context channels, four-channel EEG and three-channel PPG from a Muse 2 headband, and cabin-facing video from 23 participants, recorded in 148 trials (11.6 hours) under six induced states: Normal, Distracted, Alerted, Stressed, Relaxed, and Drowsy. We document the acquisition pipeline in detail and provide a benchmark with one protocol for all models: chronological within-subject splits, participant-disjoint cross-subject folds, validation-based model selection, and ablations over modalities, scenario-context channels, and signal normalization. Multimodal fusion reaches a macro-F1 of 0.94 for drivers seen during training. For unseen drivers, fusing driving dynamics with per-window normalized EEG/PPG raises macro-F1 from 0.408 (telemetry alone) to 0.485, consistently across all five folds, while the gap between the two protocols quantifies the inter-driver heterogeneity that personalized models must address. Multimental-IAS thus provides a concrete testbed for non-IID generalization, personalization, and federated learning in driver monitoring.
Rethinking Model Aggregation for Federated Learning with Domain Skew: A Knowledge-Preserving Perspective
arXiv cs.AIarXiv:2611.01893v1 Announce Type: cross
Abstract: Domain skew challenges federated learning by requiring a shared model to accommodate distinct visual distributions. Domain-specific experts can capture these distributions separately, creating an opportunity to integrate their representations in a unified predictor. We propose Federated Knowledge-Preserving Learning (FKPL), a two-stage framework that combines domain-oriented expert training with prototype-based classifier calibration. First, a one-shot subspace-based clustering procedure groups clients for intra-cluster training. The resulting expert encoders are concatenated and frozen, preserving each learned feature mapping during global integration. Second, clients interpolate their concatenated features with class-matched domain prototypes and upload the resulting virtual features. The server trains a global linear classifier on these features, concentrating classifier optimization at the server after a single feature upload. FKPL achieves average accuracies of 73.01\%, 67.00\%, and 64.51\% on Office-Caltech-10, PACS, and a four-domain subset of DomainNet, respectively. On DomainNet, its cross-domain standard deviation is 7.50 percentage points, the lowest among the evaluated methods. With the same concatenated extractor, prototype-based calibration improves average accuracy over federated classifier training by 9.99 and 14.94 percentage points on Office-Caltech-10 and PACS. These results identify classifier calibration as an effective way to combine preserved domain representations into a global predictor.
Privacy-Preserving ECG-HRV Emotion Classification for Mood Swing Detection using Federated Learning on Constrained Edge Devices
arXiv cs.AIarXiv:2611.01853v1 Announce Type: cross
Abstract: This paper presents a privacy-preserving mood monitoring framework that classifies emotional states from ECG-derived heart rate variability (HRV) features. The framework is evaluated on three public datasets comprising 74 participants and further validated using a wearable device in a pilot study. Leave-One-Participant-Out cross-validation (LOPO-CV) is used to assess generalization to unseen individuals. A series of experiments investigates the impact of temporal windowing, HRV feature selection, and class balancing on both four-class valence-arousal and binary valence classification. Results show that class balancing substantially improves minority-class recall, while Logistic Regression consistently outperforms five alternative classifiers and achieves competitive performance against HRV-based baselines. Pilot validation using a Polar H10 wearable achieves 75% binary valence accuracy on an unseen individual without calibration, demonstrating the feasibility of real-world deployment. To preserve privacy, the framework is also implemented using federated learning on a six-node Raspberry Pi cluster. Federated Logistic Regression achieves performance comparable to centralized training without sharing raw physiological data. These results demonstrate the potential of interpretable and privacy-preserving mood monitoring for continuous mental health assessment in clinical and community settings.
FedReady: Bounded Agents for Federation Formation
arXiv cs.AIarXiv:2611.03586v1 Announce Type: new
Abstract: Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their local data and task code for federated training or analysis. This preparation recurs when the target changes, while raw records and site-private mappings are excluded from cross-site FL messages. We present FedReady, a system that performs federation formation with bounded LLM agents. Agents propose shared contracts, local adapters, and task code; the runtime owns workflow state and accepts artifacts only after checks tied to their digests. Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission. Once participating sites and artifacts are fixed, conventional federated training or analysis proceeds without readiness agents. Across 39 simulated retinal sites and four tasks, discovery reaches recall 1.00 at precision 0.65; local eligibility verification removes all 17 false positives without losing an eligible site-task pair. The participating sites supply 45,575 task-record instances and complete four 100-round jobs, including one with a runtime-generated contract. Across ten patient cohorts, preparation supports seven patient populations and holds endpoints at three sources as unsupported. Comparison with manually prepared reference populations and analysis (the manual reference) gives a maximum survival-curve difference of 0.001133. We also analyze 19 development failures, targeted classification ablations, and standalone and heterogeneous agent configurations. These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.
Federated learning for unpaired multimodal data
arXiv cs.LGarXiv:2601.17986v2 Announce Type: replace
Abstract: Training of multimodal foundation models is currently restricted to centralized data centers containing massive, aligned datasets (e.g., image-text pairs). However, in realistic federated environments, data is often unpaired and fragmented across disjoint nodes; one node may hold sensor data, while another holds textual logs. These datasets are strictly private and share no common samples. Current federated learning (FL) methods fail in this regime, as they assume local clients possess aligned pairs or require sharing raw feature embeddings, which violates data sovereignty. We propose a novel framework to train a global multimodal transformer across decentralized nodes with disjoint modalities. We introduce a small public anchor set to align disjoint private manifolds. Using Gram matrices calculated from these public anchors, we enforce semantic alignment across modalities through centered kernel alignment without ever transmitting private samples, offering a mathematically superior privacy guarantee compared to prototype sharing. Further, we introduce a subspace-stabilized fine-tuning method to handle FL with huge transformer models. We strictly decouple domain-specific magnitude shifts from semantic direction, ensuring that nodes with varying sensor characteristics align geometrically to the global consensus. Lastly, we propose precision weighted averaging, where efficiently obtained uncertainty estimates are used to downweight uncertain nodes. This paper establishes the mathematical backbone for federated unpaired foundation models, enabling a global model to learn a unified representation of the world from fragmented, disjoint, and private data silos without requiring centralized storage or paired samples.
AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning
arXiv cs.LGarXiv:2610.41278v1 Announce Type: cross
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.
Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities
arXiv cs.LGarXiv:2610.41193v1 Announce Type: new
Abstract: Multimodal federated learning (MFL) trains a shared model by aggregating client updates without exchanging raw data. Under missing modalities, clients adapt active modality encoders and a shared prediction block (fusion and classifier) to different input subsets. This raises two server-side questions: which clients should contribute to each component, and how should their aggregates be incorporated across rounds? We observe that an absent-modality encoder can still adapt through missing-input handling. Availability- based aggregation can therefore omit its update while retaining jointly learned prediction-block updates. Contributor selection also shapes server momentum, a weighted history of aggregated updates. We observe that prediction-block momentum can improve or reduce performance depending on the encoder update policy. We therefore propose Role-Aware Server Optimization (RASO), which coordinates contributor selection with role-specific server updates. RASO selects contributors through prediction dependence and inclusion in local optimization, retains encoder momentum, and synchronizes the shared prediction block to its current aggregate. Experiments across datasets and fusion architectures demonstrate the effectiveness of RASO under missing modalities.
MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation
arXiv cs.CVarXiv:2605.04108v2 Announce Type: replace
Abstract: Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning further partitions the model between clients and a server to reduce computation and communication at the client side. However, decentralized medical institutions rarely operate on a single shared task, making standard Federated and SplitFed collaborations poorly aligned with real clinical workflows. Multi-task FL extends these frameworks by allowing clients to handle different tasks, but often introduces instability and privacy vulnerabilities. This study proposes \textbf{MuCALD-SplitFed}, a multi-task SplitFed framework that integrates causal representation learning and latent diffusion. Experiments show MuCALD-SplitFed consistently improves segmentation, while baseline SplitFed fails to converge. The proposed approach further reduces information leakage at split points, mitigating reconstruction-based and membership inference attacks. Additionally, MuCALD SplitFed outperforms state-of-the-art personalized FL and multi-task FL approaches. The code repository is: https://github.com/ChamaniS/MuCALD_SplitFed.
Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs
arXiv cs.AIarXiv:2610.41039v1 Announce Type: cross
Abstract: As Mixture-of-Experts (MoE) large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored landscape of security vulnerabilities. Moving beyond textual analysis, we uncover structural memorization: a novel vulnerability where a fine-tuned model memorizes not only its training data but also the internal pathway used to process it, creating a characteristic routing fingerprint unique to the training process. We provide comprehensive empirical evidence that structural memorization emerges consistently even from a few samples, and that its intensity is directly influenced by the choice of trainable modules.
We show that these memorized expert pathways can be stealthily recovered through the model's unconditional generation, using only routing and output logits, with no knowledge of the fine-tuning data or procedure. In distributed deployments, this vulnerability is amplified as routing information is exposed at multiple trust boundaries, including federated aggregation points, edge-cloud interfaces, and multi-tenant monitoring systems. Recovery exposes a critical blind spot: traditional membership inference metrics, viewed through the lens of expert routing, fail to identify memorized data corresponding to these structural pathways. To close this gap, we devise composite metrics combining reference model tail likelihood with complexity-aware normalization, significantly improving detection of memorized routing structures. This enables adversaries to pinpoint critical experts shaped by fine-tuning, whether dominant or dormant, and execute targeted attacks such as router manipulation or backdoor injection in realistic distributed settings where attackers lack training data but can observe routing patterns across system components.
Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning
arXiv cs.AIarXiv:2506.20651v1 Announce Type: cross
Abstract: Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global model to provoke information-rich updates from clients. In this paper, we adopt a defender's perspective to provide the first comprehensive analysis of malicious gradient leakage attacks and the model manipulation techniques that enable them. Our investigation reveals a core trade-off: these attacks cannot be both highly effective in reconstructing private data and sufficiently stealthy to evade detection -- especially in realistic FL settings that incorporate common normalization techniques and federated averaging.
Building on this insight, we argue that malicious gradient leakage attacks, while theoretically concerning, are inherently limited in practice and often detectable through basic monitoring. As a complementary contribution, we propose a simple, lightweight, and broadly applicable client-side detection mechanism that flags suspicious model updates before local training begins, despite the fact that such detection may not be strictly necessary in realistic FL settings. This mechanism further underscores the feasibility of defending against these attacks with minimal overhead, offering a deployable safeguard for privacy-conscious federated learning systems.
Connectivity-Aware Client Selection in Decentralized Federated Learning
arXiv cs.AIarXiv:2610.41570v1 Announce Type: new
Abstract: Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server. However, most existing decentralized approaches rely on full-neighborhood broadcasting, where each client transmits its model update to all of its neighbors in each communication round. While effective, this results in significant communication overhead and high energy consumption. This paper applies spectral graph tools as lightweight client selection methods that leverage the graph topology by analyzing the spectral properties of the graph Laplacian over a fixed communication graph. Specifically, we exploit eigenvector embeddings and heat/diffusion kernel similarities to guide each client in selecting only a subset of structurally relevant neighbors, i.e., those that are most beneficial for the convergence of the federation process. This topology aware randomization matches or outperforms uniform neighborhood subsampling and approaches the accuracy of full broadcasting. The largest gains, about $3$ percentage points, emerge under strong data heterogeneity on larger, structurally rich graphs, while the total number of transmitted messages is reduced by $50\%$ compared to naive broadcasting.
Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
arXiv cs.AIarXiv:2610.39483v1 Announce Type: new
Abstract: Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organizations, putting privacy and the transparency demanded by forensic review in direct conflict. Federated learning resolves the privacy side by sharing only model updates rather than raw data, but whether this comes at the cost of trustworthy gradient-based explanations, which analysts rely on to decide whether or not to trust a flagged clip, has not been studied. We present the systematic study of Grad-CAM explanation faithfulness under federated deepfake detection, evaluating an EfficientNet-B4 detector on FaceForensics++ across five federated clients under varying degrees of data heterogeneity. We find that the relationship between federation and explanation quality is non-monotonic: at near-IID (Independent and Identically Distributed Data) and moderate heterogeneity, federated models match or exceed the faithfulness of a centralized baseline, but at extreme heterogeneity, explanations break down entirely, becoming spatially incoherent and, on average, causally misleading. This degradation is not a general cost of federated training but a threshold effect tied to client heterogeneity, and we offer practical guidance for identifying when privacy-preserving deepfake detection can be deployed safely and when its explanations can no longer be trusted. Code and data partitions are available for reproducibility.
Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
arXiv cs.AIarXiv:2610.38411v1 Announce Type: new
Abstract: 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.
FedHQ: Hybrid Runtime Quantization for Federated Learning
arXiv cs.LGarXiv:2505.11982v2 Announce Type: replace
Abstract: Federated Learning (FL) must balance training efficiency and model accuracy across heterogeneous clients. Post-training quantization (PTQ) avoids the extra computation of quantization-aware training (QAT), but can incur greater accuracy loss. We propose FedHQ, a hybrid quantization framework that assigns PTQ or QAT according to clients' hardware and data characteristics. Hardware-based speed estimates and local data-distribution indicators guide coarse-grained global initialization, followed by fine-grained training-based adjustment of selected client strategies. Experiments on three image-classification datasets show that FedHQ achieves up to 2.47x training speedup over FedAQT and up to 11.15 percentage points higher accuracy than FedFQ.
Data-Driven Laplacian-Constrained Personalized Federated Learning
arXiv cs.LGarXiv:2505.07575v3 Announce Type: replace
Abstract: Personalization addresses one of the defining challenges in federated learning: statistical heterogeneity among clients. We show that the dissimilarity between the ideal personalized models of two clients can be upper bounded by the dissimilarity of their distributions. Motivated by this, we propose Karula, a data-driven regularization method that constrains pairwise model dissimilarities between clients according to their distributional differences. Distributional similarity is measured using a surrogate for the 1-Wasserstein distance adapted for the federated setting, allowing the method to adapt to highly complex interrelations between clients that approaches based on hard clustering may fail to recover. We propose an approximate projected stochastic gradient algorithm to solve the resulting constrained optimization problem, and prove that it converges at a rate of $O(1/K)$ to a neighborhood of a stationary point.
Split Federated Unlearning
arXiv cs.LGarXiv:2610.36465v1 Announce Type: new
Abstract: Split federated learning (SFL) combines partitioned model execution with federated aggregation to support collaborative learning across distributed Web and edge environments. However, removing learned contributions in SFL is challenging due to cross-partition coupling and historical influence propagation through dual-side aggregation. To the best of our knowledge, we provide the first systematic formulation of Split Federated Unlearning (SFU), encompassing client-wise and class-wise removal, counterfactual retraining, and partition-specific update constraints. We theoretically characterize historical influence propagation and mode-dependent unlearning feasibility, revealing structural limitations of restricted model updates. As an initial solution, we propose SURE, integrating dual-importance estimation, selective parameter perturbation, and importance-guided recovery. Extensive experiments with existing unlearning methods adapted to SFL reveal substantial forgetting-utility trade-offs across model architectures, data distributions, and update modes. SURE achieves competitive agreement with mode-matched retraining at modest additional cost, while further analyses highlight the impact of split position and update constraints on unlearning behavior. These findings establish SFU as a distinct research problem and provide a foundation for unlearning in partitioned federated systems.
Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging
arXiv cs.CVarXiv:2610.36379v1 Announce Type: new
Abstract: Artificial intelligence (AI) shows promise for breast imaging, but limited labeled data, institutional data fragmentation, and privacy concerns hinder centralized training. We investigate a privacy-aware federated learning framework combining pretrained vision-language models (VLMs) with client-level differential privacy. We compare general-purpose CLIP models, biomedical BiomedCLIP, and an ImageNet-pretrained ViT-B/16 baseline on two public breast imaging datasets, with and without differential privacy. We also evaluate a CLIP ViT-B/16 ablation that removes the text pathway. Evaluation includes patient-level ROC-AUC with bootstrap 95% confidence intervals, baseline comparisons, threshold sensitivity, inter-model agreement, and communication cost. Under federated learning, all five models achieve high normal-versus-sick discrimination (ROC-AUC: 0.940-0.990). However, acquisition year alone achieves 0.974 on the same test partition, raising concerns about confounding rather than genuine pathology recognition. Benign-versus-malignant discrimination remains uncertain (ROC-AUC: 0.504-0.637), with all confidence intervals including 0.50. Removing the text pathway preserves classification accuracy while halving communication cost. Differential privacy reduces ROC-AUC by 0.375, attributable to perturbing the full model state rather than only trainable parameters. These findings highlight the importance of evaluating confounding, predictive reliability, privacy implementation, and deployment efficiency when developing federated AI systems for breast imaging.
继续滚动加载更多…