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.
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: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. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.
The paper argues that evaluating anonymity in synthetic data generation must focus on the generative model rather than just the resulting dataset. It interprets GDPR definitions of personal data and anonymization under realistic model-access scenarios, mapping these to state‑of‑the‑art privacy attacks. The authors conclude that synthetic data alone is insufficient for anonymization, and that Differential Privacy offers stronger protection than Similarity‑based Privacy Metrics.
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
FedSumUp introduces a learnable lossy compressor that generates compact, visually interpretable representations on client devices, reducing privacy leakage and computational overhead. The compressor is trained on the server using a data‑free closed‑loop optimization that minimizes the difference between original and twice‑compressed representations after upsampling. Experiments on BloodMNIST, CIFAR‑10, and ChestMNIST show low reconstruction PSNR, significant client runtime reductions, and competitive classification accuracy while remaining robust to non‑IID data.
The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.
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...
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.
arXiv:2606. 18518v1 Announce Type: cross Abstract: The development of medical AI is constrained by limited access to high-quality clinical data due to institutional silos and strict privacy regulations such as HIPAA and GDPR.
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...
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.