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.
hub
Differentially Private Federated Learning: A Client Level Perspective
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to share the data. However, the protocol is vulnerable to differential attacks, which could originate from any party contributing during federated optimization. In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model. We tackle this problem and propose an algorithm for client sided differential privacy preserving federated optimization. The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance. Empirical studies suggest that given a sufficiently large number of participating clients, our proposed procedure can maintain client-level differential privacy at only a minor cost in model performance.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
DMBA maintains attack success rates above 80% for all backdoors in a distributed multi-target FL setting where baselines drop below 50%.
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.
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.
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.
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.
CausShield decomposes VFL representations via causal representation learning to resist sample reconstruction attacks while preserving utility and convergence.
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.
Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.
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.
RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.
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.
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.
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.
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.
A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.
citing papers explorer
-
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
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.
-
DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models
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.
-
Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning
DMBA maintains attack success rates above 80% for all backdoors in a distributed multi-target FL setting where baselines drop below 50%.
-
Convergent Differential Privacy Analysis for General Federated Learning
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.
-
Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
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.
-
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
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.
-
Robust Federated Learning Under Real-World Client Churn
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.
-
CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning
CausShield decomposes VFL representations via causal representation learning to resist sample reconstruction attacks while preserving utility and convergence.
-
DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning
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.
-
Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.
-
Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience
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.
-
Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.
-
DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
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.
-
Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
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.
-
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
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.
-
FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
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.
-
Compliance Management for Federated Data Processing
A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.