The paper analyzes language generation and identification in the limit under bounded memory, showing that memory constraints significantly alter learnability, particularly affecting achievable density…

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…

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…

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.

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper introduces a novel, efficient mechanism based on permute-and-flip for applying differential privacy to symbolic state trajectories, significantly reducing the computational overhead compared…

The paper proposes an empirical calibration method, TeDA, to provide a more comparable and interpretable assessment of privacy loss for text rewriting mechanisms under Local Differential Privacy (LDP)…

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 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 proposes a character-level differential privacy mechanism to sanitize sensitive user prompts for LLMs, achieving high privacy for PII while maintaining utility for non-sensitive context.

The paper introduces LLM-CEG, an extended framework that uses membership inference attack success rates and model perplexity to systematically audit and optimize the privacy-utility trade-off when fin…

This paper corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.

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 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.

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 provides the first theoretical convergence analysis for machine learning training under fully homomorphic encryption combined with differential privacy, improving efficiency and scalability.

The paper introduces novel, efficient differentially private algorithms for estimating monotone statistics, significantly improving sample complexity compared to existing methods.

The paper develops a unified theoretical framework to systematically characterize the optimal privacy-utility trade-off (PUT) and optimal Local Differential Privacy (LDP) channels for general statisti…