{"total":17,"items":[{"citing_arxiv_id":"2607.07565","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-07-08T15:56:58+00:00","verdict":"CONDITIONAL","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competitive global models in one communication round.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.06979","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Robust Federated Learning Under Real-World Client Churn","primary_cat":"cs.LG","submitted_at":"2026-07-08T04:02:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FeLiX reduces wall-clock time-to-target accuracy in federated learning by up to 2.37x using lightweight availability tiers, fresh-utility client selection, and informativeness-aware aggregation without requiring oracular knowledge of client availability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18312","ref_index":52,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization","primary_cat":"cs.CR","submitted_at":"2026-06-16T10:24:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TIGER turns the low-rank attention gradient subspace into a differentiable objective for continuous embedding optimization, improving reconstruction quality and robustness over prior discrete token tests especially under noise or DP.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08027","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning","primary_cat":"cs.LG","submitted_at":"2026-06-06T07:40:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CausShield decomposes VFL representations via causal representation learning to resist sample reconstruction attacks while preserving utility and convergence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04899","ref_index":71,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning","primary_cat":"cs.CR","submitted_at":"2026-06-03T14:01:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DIST-FL distributes TEE-guarded servers into an append-only ledger to ensure linearizable FL aggregation and counter rollback plus I/O attacks while matching single-TEE speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18656","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning","primary_cat":"stat.ML","submitted_at":"2026-05-18T17:01:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10272","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:32:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"DP-LAC provides a new adaptive clipping technique for DP-SGD in federated LLM fine-tuning that improves accuracy by 6.6% on average without consuming additional privacy budget or requiring new hyperparameters.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"\"Differentially private learning with adaptive clipping,\"NeurIPS, vol. 34, pp. 17455-17466, 2021. [18] M. Qiu, X. Liang, and R. Du, \"Aodpfl: An adaptive optimization method for differentially private federated learning,\" inSMC. IEEE, 2024, pp. 1976-1983. [19] J. Liu and K. Talwar, \"Private selection from private candidates,\" inSTOC. 2019, pp. 298-309, ACM. [20] N. Papernot and T. Steinke, \"Hyperparameter tuning with renyi differential privacy,\" inICLR. 2022, OpenReview.net. [21] Z. Bu and R. Liu, \"Towards hyperparameter-free optimization with differential privacy,\" inICLR. 2025, OpenReview.net. [22] L. Bottou, F. E. Curtis, and J. Nocedal, \"Optimization methods for large-scale machine learning,\"SIAM review, vol."},{"citing_arxiv_id":"2604.27833","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning","primary_cat":"cs.CV","submitted_at":"2026-04-30T13:20:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VPDR improves the privacy-utility trade-off in ProtoPFL by allocating less noise to high-variance discriminative prototype dimensions via VPP and using DCR to keep feature norms near the clipping threshold without harming predictions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23426","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","primary_cat":"cs.CV","submitted_at":"2026-04-25T19:43:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Adaptive bit-length schedulers plus Laplacian DP in non-IID FL reduce communicated data by up to 52.64% on MNIST and 45% on CIFAR-10 while keeping competitive accuracy and privacy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22885","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization","primary_cat":"cs.CV","submitted_at":"2026-04-24T08:31:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07125","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation","primary_cat":"cs.CR","submitted_at":"2026-04-08T14:19:39+00:00","verdict":"CONDITIONAL","verdict_confidence":"HIGH","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A blacklist/whitelist-guided prompt optimization plus diffusion pipeline produces de-identified chest X-rays that retain enough pathology for competitive report-generation training while cutting patient-identity classifier accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06297","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs","primary_cat":"cs.CR","submitted_at":"2026-04-07T17:19:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedSpy-LLM uses gradient decomposition and iterative alignment to reconstruct larger batches and longer sequences of training data from LLM gradients in federated settings, including with PEFT methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.03853","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience","primary_cat":"quant-ph","submitted_at":"2026-03-04T09:04:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.19945","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models","primary_cat":"cs.LG","submitted_at":"2026-02-23T15:15:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DP-FedAdamW delivers an unbiased second-moment estimator for AdamW in DPFL, proving linear convergence acceleration without heterogeneity assumptions and outperforming SOTA by 5.83% on Tiny-ImageNet with Swin-Base at ε=1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.19360","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Compliance Management for Federated Data Processing","primary_cat":"cs.SE","submitted_at":"2026-02-22T22:10:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.03926","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning","primary_cat":"cs.CV","submitted_at":"2024-11-06T13:57:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DMBA maintains attack success rates above 80% for all backdoors in a distributed multi-target FL setting where baselines drop below 50%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.15621","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Convergent Differential Privacy Analysis for General Federated Learning","primary_cat":"cs.LG","submitted_at":"2024-08-28T08:22:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proves convergent privacy bounds for Noisy-FedAvg and stable lower bounds for Noisy-FedProx in FL-DP via f-DP and shifted interpolation, replacing divergent composition bounds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}