LLMs AND DATA PRIVACY

Integrity Checking Mechanism for PrivacyPreserved Auditing of Cloud Shared-Data

A viable, privacy-friendly auditing framework of clouds which guarantees the end-toend encrypted verification without sacrificing the efficiency is presented.

Regression on encrypted datasets using fully homomorphic encryption 1

The results of the experiments show that the hardware-accelerated implementation of the FHE primitives speeds up the encrypted gradient descent algorithm significantly.

Secure Cloud-based EHR Analytics using a Hybrid Homomorphic Encryption and Differential Privacy Pipeline

A Survey on Privacy-Preserving Techniques for Cloud Data Processing Using Homomorphic Encryption and Federated Learning

This paper presents a structured review of privacy-preserving data processing techniques for cloud environments built on HE and FL, individually and in hybrid combination, and identifies promising directions for future research.

Doppio : Communication-Efficient and Secure Multi-Party Shuffle Differential Privacy

The augmented multi-party shuffle DP (AMP-SDP) model is proposed, which re-architects the data pipeline with a lightweight, versatile secret-shared intermediary layer that decentralizes trust while minimizing online communication costs and provides structural security hardening against both shuffler compromise and user-sid...

SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

User prompts provided to large language models (LLMs) may contain sensitive or private information that can be misused by remotely deployed models, such as through inadvertent memorization during retraining. One way to protect user prompts is to execute the LLM inside a trusted execution environment (TEE), with the gua...