arXiv:2607. 05866v1 Announce Type: cross Abstract: Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency.
By Pan Li, Kai Chen, Shuai Chang, Shengzhi Zhang, Peizhuo Lv, Jinwen He
arXiv:2601. 04710v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation.
By Feihu Jin, Shipeng Cen, Ying Tan
The paper introduces a per-layer differential privacy (DP) clipping strategy for federated multilingual speech large language models (speech‑LLMs). It demonstrates that standard single‑pool per‑layer DP methods fail due to a cross‑component budget collapse caused by large norm differences between acoustic encoders and language decoders. The authors propose an α‑split two‑pool allocation that normalises encoder and decoder parameters separately, preserving the overall DP guarantee while restoring word error rate performance and providing tighter noise protection for the encoder.
By Jordi Luque, Fernando L\'opez, Aleix Sant
arXiv:2407. 08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning.
By Ding Chen, Haochen Luo, Xiaofei Wang, Chen Liu
arXiv:2602. 06838v3 Announce Type: replace Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy.
By Jin Wang, Hui Ma, Yajun Zhang, Xinjun Pei, Ming Yan, Fei Xing, Yikun Chen
arXiv:2609.40335v1 Announce Type: new
Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). M...
By Razan El Mais, Ali Chehab, Ibrahim Issa, Razane Tajeddine