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.
PrivacyFlow introduces a new benchmark, PrivacyBench, and a defense system that separates privacy planning from task execution in autonomous LLM agents. The system traces data provenance, models recipient knowledge, and simulates inference attacks to weigh disclosure risk against task utility, allowing it to minimize or block data sharing. Experiments show that PrivacyFlow reduces privacy failures and increases completed task sequences by 22–55 percentage points, while revealing a tradeoff between privacy, utility, and user autonomy.
arXiv:2510. 04902v3 Announce Type: replace Abstract: Tuning hyperparameters in federated machine learning can substantially impact model performance.
Autonomous LLM agents executing multi-step workflows over personal data often misalign with user privacy expectations and leak sensitive, out-of-context information. Although Contextual Integrity (CI)...
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.
The paper introduces DP‑µP, a framework that extends Maximal Update Parametrization to differential privacy settings. By analyzing gradient clipping, noise injection, and feature learning, it derives a signal‑to‑noise ratio condition and spectral scaling rules for DP‑SGD, DP‑Adam, and DP‑Muon optimizers. Experiments show that DP‑µP enables zero‑shot transfer of learning rates across model widths on MLP, ViT, and GPT‑2, matching or surpassing tuned baselines while cutting computational costs.
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.