The field of privacy-preserving computing and cryptography is rapidly advancing, with a focus on developing innovative solutions to protect sensitive data and ensure secure computation. Recent developments have centered around fully homomorphic encryption (FHE), trusted execution environments (TEEs), and secure multi-party computation. Notably, researchers have been exploring the application of FHE in various domains, including database systems and machine learning. Furthermore, the use of TEEs has been gaining traction as a means to provide secure execution environments for sensitive computations. In addition, there has been significant progress in the development of more efficient and scalable cryptographic protocols, such as hybrid homomorphic encryption and format-preserving encryption. These advances have the potential to enable secure and private computation in a wide range of applications, from cloud computing to edge devices. Noteworthy papers include FHE-SQL, which enables secure query processing on encrypted data, and SecureInfer, a heterogeneous TEE-GPU architecture for privacy-critical tensors in large language model deployment. Another notable work is HHEML, a hybrid homomorphic encryption framework for privacy-preserving machine learning on edge devices.
Advances in Privacy-Preserving Computing and Cryptography
Sources
Partitioning $\mathbb{Z}_{sp}$ in finite fields and groups of trees and cycles
FHE-SQL: Fully Homomorphic Encrypted SQL Database
Resource Estimation of CGGI and CKKS scheme workloads on FracTLcore Computing Fabric
DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge
Cryptanalysis of a Privacy-Preserving Ride-Hailing Service from NSS 2022
Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
Comparison and performance analysis of dynamic encrypted control approaches
Single-Shuffle Full-Open Card-Based Protocols for Any Function
From See to Shield: ML-Assisted Fine-Grained Access Control for Visual Data
Privacy-Preserving Spiking Neural Networks: A Deep Dive into Encryption Parameter Optimisation
Analysis and Comparison of Known and Randomly Generated S-boxes for Block Ciphers
SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge
Privacy Protection of Automotive Location Data Based on Format-Preserving Encryption of Geographical Coordinates