arXiv AI October 12, 2026 By Zhihao Liu, Yitian Cheng, Shuang Liu, Rui Wen, Yuke Hu, Zhan Qin

DP-MIND: Differentially private memory-guided Long context Inference

DP-MIND is a memory‑guided framework that enables differentially private inference for large language models on million‑token contexts. It locally perturbs user queries and processes them in chunks, using a compact memory that retains task‑relevant information across the sequence. The memory construction is optimized via reinforcement learning on perturbed inputs, and a local denoising module recovers corrupted answer spans, resulting in improved scalability and utility over existing DP and long‑context inference baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

1d ago

Guided Diffusion for Trustworthy Synthetic Text Generation

arXiv:2610.27259v1 Announce Type: cross Abstract: The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently...

By Qi Pang, Hanshen Xiao, Andre Manoel, Lipika Ramaswamy, Wenting Zheng, Virginia Smith, G. Edward Suh

llms rag diffusion fine-tuning safety

arXiv AI

Jun 4

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.

By Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang

llms safety

arXiv Machine Learning

Oct 2

Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?

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

llms rag fine-tuning safety

arXiv Machine Learning

Aug 4

MAPLE: Metadata Augmented Private Language Evolution

arXiv:2603. 19258v2 Announce Type: replace-cross Abstract: Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users.

By Eli Chien, Yuzheng Hu, Ryan McKenna, Shanshan Wu, Zheng Xu, Peter Kairouz

llms fine-tuning benchmarks safety

arXiv Machine Learning

Oct 2

SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs

The paper introduces SparLeak, a side‑channel attack that exploits a new GPU micro‑architectural leakage called Sparsity‑Induced Memory Access (SIMA) caused by sparse attention in large language models. By capturing SIMA traces during LLM inference, SparLeak can infer user‑query attributes from prefill‑phase traces and reconstruct autoregressive responses from decoding‑phase traces. Experiments on three LLM architectures, three sparse attention mechanisms, and three privacy‑sensitive datasets show high success rates (90.9% for attribute inference and 87.3% for response reconstruction), underscoring the need to address SIMA leakage in sparse‑attention deployments.

By Fahao Chen, Linkang Du, Jinhao Zhou, Peng Li, Zhou Su

llms efficiency safety

arXiv AI

Aug 17

P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems

arXiv:2608. 14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices.

By Myunghoon Ryu, Geunpyo Park, Sungjoon Lee, XinYu Piao, Jong-Kook Kim

llms fine-tuning efficiency benchmarks safety

One email a morning, machine-written

Related stories

Guided Diffusion for Trustworthy Synthetic Text Generation

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?

MAPLE: Metadata Augmented Private Language Evolution

SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs

P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems