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 shows that using random cropping, a standard data augmentation technique, can naturally amplify differential privacy guarantees for machine learning models without requiring any changes to t…

The paper proposes DP-GCL, a novel differentially private contrastive learning framework that improves representation learning on sensitive data by bounding gradient dependency through localized group…

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…

The paper proposes a Jacobian-guided anisotropic noise reshaping technique to selectively attenuate noise in task-relevant subspaces, significantly enhancing data utility while maintaining Local Diffe…

The paper proposes DP-MacAdam, a novel differentially private optimization algorithm that simultaneously uses adaptive gradient clipping and momentum, achieving improved model accuracy over existing m…

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…

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 introduces a differentially private manifold denoising framework that allows noisy, non-private query points to be corrected using sensitive reference data while providing formal $(\varepsil…

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper proposes PAC-DP, a personalized adaptive clipping framework that dynamically adjusts gradient clipping thresholds based on the desired privacy budget, significantly improving the privacy-uti…

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 introduces Fractional-Order Differentially Private Stochastic Gradient Descent (FO-DP-SGD), a mechanism that incorporates fractional memory into the gradient release process to improve priva…

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…

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 introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.

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 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…