The paper introduces ‘DP-SPIN’, a trusted‑curator framework that generates differentially private semantic plans for aggregate insight generation. ‘DP-SPIN’ maps each record to a bounded sparse nonnegative vector over pre‑defined semantic concepts, sums these vectors into a semantic sketch, and releases a noisy plan containing admitted concepts and their masses. The framework provides user‑level privacy by clipping each user’s contribution and ensures that the final summary is differentially private through post‑processing, with guarantees established under both add/drop and replacement adjacency.
By Behrooz Razeghi
CALLIOPE is a new top‑down framework designed to uncover topic hierarchies in large unstructured datasets, such as LLM conversations, while ensuring differential privacy. Unlike conventional methods that depend on clustering vector embeddings, CALLIOPE directly employs LLM capabilities throughout its pipeline. Experiments show that CALLIOPE delivers higher utility than embedding‑based approaches, particularly in high‑privacy scenarios, and its outputs are evaluated using both standard clustering metrics and newly introduced utility metrics.
By Edith Cohen, Vadym Doroshenko, Badih Ghazi, Charlie Harrison, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Mikhail Pravilov, Adam Sealfon, Yurii Sushko, Marika Swanberg, Chiyuan Zhang
arXiv:2609.38934v1 Announce Type: cross
Abstract: Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement car...
By Tsubasa Takahashi, Takumi Hiraoka
The paper introduces a lightweight privacy-preserving technique for Retrieval-Augmented Generation (RAG) systems that uses random projection to transform both datastore and query embeddings. This approach maintains semantic similarity for effective retrieval while significantly reducing the risk of data extraction attacks. Experiments across various RAG architectures and datasets demonstrate that the method outperforms prior differential privacy-based techniques in both retrieval and generation performance while offering comparable empirical privacy.
By Dixi Yao, Tahseen Rabbani, Tian Li
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
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
By Lorenzo Rossi, Bart{\l}omiej Marek, Franziska Boenisch, Adam Dziedzic
arXiv:2606. 04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is context agnostic and may raise two issues: over disclosing untyped sensitive context and over removing answer bearing spans.
By Xinyue Huang, Xiaochun Cao, Wenyuan Yang
Efficient Provably Private Classification with a Tabular Foundation Model introduces PrivTab, a tabular foundation model that embeds differential privacy directly into its architecture. Pretrained on simulated datasets, PrivTab uses in-context learning to convert sensitive rows into compact, provably private summaries, enabling a single forward pass for classification. The model outperforms private linear and neural‑network baselines under moderate-to-strong privacy, shows negligible membership leakage, maintains well‑calibrated predictions, and reduces dataset fitting time by 10,000×.
By Talal Alrawajfeh, Cristiana Diaconu, Ossi R\"ais\"a, Sebastian Rodriguez Beltran, Yuan He, John Bronskill, Richard E. Turner, Antti Honkela
arXiv:2606. 08259v1 Announce Type: new Abstract: This paper investigates the problem of generating synthetic tabular data with differential privacy (DP) guarantees, enabling data sharing in sensitive domains.
By Toan Tran, Arturs Backurs, Zinan Lin, Victor Reis, Li Xiong, Sergey Yekhanin
The paper introduces a federated inference framework that enables multiple commercial large language model (LLM) APIs—such as LLaMA‑3.3‑70B, GPT‑4o‑mini, and Claude‑3‑Haiku—to collaborate on cognitive diagnosis tasks without accessing raw student data or proprietary model internals. Each entity’s predictions are perturbed with Laplace noise to provide epsilon‑local differential privacy, and a residual‑based aggregation scheme mitigates model heterogeneity. Experiments on three educational benchmarks demonstrate strong privacy guarantees with minimal accuracy loss, confirming the framework’s practical usability and cross‑domain generalizability.
By Yagna Manasa Boyapati, Chong Yu, Tianyu Jiang, Justin Zhan
The paper compares data-level and training-level methods for balancing language model capability and privacy leakage on synthetic medical records with embedded canaries. Direct finetuning achieves the highest capability but leaks the most private information, while DP‑SGD reduces leakage at a significant cost to performance. Generating privacy‑aware synthetic data—especially with uniqueness‑aware rewriting—offers a better trade‑off, and more capable rewriting models tend to lower downstream privacy risks, though gains are inconsistent with increased compute.
By Zihao Zhao, Avi Schwarzschild, Casey Meehan, Katherine Lee, Zhili Feng, Dylan Sam
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
By Kareem Amin, Rudrajit Das, Alessandro Epasto, Adel Javanmard, Dennis Kraft, M\'onica Ribero, Sergei Vassilvitskii