arXiv:2606. 31474v1 Announce Type: new Abstract: Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions.
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.
arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...
arXiv:2606. 16952v1 Announce Type: 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.
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
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.
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
arXiv:2512. 12840v2 Announce Type: replace-cross Abstract: Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces.
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.
The paper introduces PrivaTree, a differentially‑private decision tree algorithm that uses private histograms to select splits while preserving a small privacy budget. PrivaTree supports mixed numerical and categorical data without leaking information about numerical features and achieves a superior privacy‑utility trade‑off compared to existing methods. Additionally, the authors provide theoretical bounds on the expected accuracy and success rates of backdoor attacks, showing that PrivaTree-trained trees are more robust against data poisoning than standard decision trees.
arXiv:2310. 16152v5 Announce Type: replace-cross Abstract: Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis.
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.