ProjRes achieves near-100% accuracy in membership inference on FedLLMs by measuring projection residuals of hidden embeddings on gradient subspaces, outperforming prior methods by up to 75.75% even under differential privacy.
Dp-dylora: Fine-tuning transformer-based models on-device under differentially private federated learning using dynamic low-rank adaptation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
FedPower improves the accuracy-privacy tradeoff in differentially private LoRA-based federated learning by reconstructing and clipping full-rank updates then using PowerDP to inject noise before orthonormalization in low-rank factorization.
PINA improves accuracy in differentially private clustered federated learning by an average of 2.9% using privacy-preserving LoRA sketches for cluster initialization and normality-driven aggregation.
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.
FedShield-LLM integrates pruning and FHE on LoRA parameters to support secure, scalable federated fine-tuning of LLMs such as Llama-2.
citing papers explorer
-
Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
ProjRes achieves near-100% accuracy in membership inference on FedLLMs by measuring projection residuals of hidden embeddings on gradient subspaces, outperforming prior methods by up to 75.75% even under differential privacy.
-
Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
FedPower improves the accuracy-privacy tradeoff in differentially private LoRA-based federated learning by reconstructing and clipping full-rank updates then using PowerDP to inject noise before orthonormalization in low-rank factorization.
-
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
PINA improves accuracy in differentially private clustered federated learning by an average of 2.9% using privacy-preserving LoRA sketches for cluster initialization and normality-driven aggregation.
-
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.
-
FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
FedShield-LLM integrates pruning and FHE on LoRA parameters to support secure, scalable federated fine-tuning of LLMs such as Llama-2.