The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consu…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper quantifies the cost of privacy in language identification and generation using differentially private (DP) methods, finding that the cost is surprisingly mild, particularly absent under appr…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

DPDSyn improves differentially private dataset synthesis by training a differentially private AI model on the original private data, which is then used to generate synthetic datasets that maintain hig…

This paper provides a systematic, lifecycle-based framework for analyzing security threats and defenses across the entire fine-tuning process of LLMs, revealing that attack effectiveness is highly mod…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive…

The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…

The paper introduces PACZero, a novel PAC-private fine-tuning mechanism that achieves usable utility for large language models while providing strong resistance against membership-inference attacks.

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

DP-SAPF introduces a saliency-aware parameter fine-tuning method that selectively identifies the most critical parameters for LoRA training, significantly improving the utility and fidelity of differe…

The paper proposes SELFCI, a complementary self-distillation framework that effectively balances the privacy requirements of Contextual Integrity (CI) with the utility of large language models, outper…

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

The paper proposes FedPower, a novel differentially private cross-silo Federated Learning framework that uses PowerDP to reconstruct and project client updates into a secure low-rank space, effectivel…

The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…

The paper proposes DPSR-CG, a novel differentially private selective release mechanism that rigorously maintains strict privacy guarantees while significantly improving model utility compared to exist…