The paper investigates how differential privacy (DP) affects the ability to merge independently fine‑tuned task models into a single multi‑task model. It identifies two geometric challenges—local sharpness and reference drift—that hinder mergeability of private models. To address these, the authors propose DP‑Merging, a framework that uses a sharpness‑aware objective and a reference‑based alignment regularizer to improve mergeability while maintaining DP guarantees.
arXiv:2606. 18996v1 Announce Type: cross Abstract: Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.
arXiv:2609.05770v1 Announce Type: new Abstract: Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see a...
arXiv:2601. 17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data.
arXiv:2510. 04902v3 Announce Type: replace Abstract: Tuning hyperparameters in federated machine learning can substantially impact model performance.
Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets.
arXiv:2606. 02563v1 Announce Type: new Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity.
arXiv:2607. 07471v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness.
Geometric Data Perturbation (GDP) allows participants to share distance‑preserving transformations of their private data for one‑shot collaborative learning. The paper examines the vulnerability when an analyst colludes with participants, showing that shared‑anchor alignment can restore compatibility but also enables exact data recovery. To mitigate this, the authors propose adding noise to the anchor representations rather than the private data, demonstrating through experiments on MNIST and CelebA that this approach yields better privacy‑utility trade‑offs under collusion.
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
arXiv:2601. 11219v3 Announce Type: replace-cross Abstract: Federated learning (FL) for large language models (LLMs) has attracted increasing attention as a privacy-preserving approach for adapting models over distributed data, where parameter-efficient methods such as Low-Rank Adaptation (LoRA) are widely adopted to reduce communication and memory costs.