4 papers
ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation
Jiangrui Yu, Baosheng Zhang, Liang Kong +5
Generative large language models (LLMs) have achieved state-of-the-art performance on many real-world tasks such as code generation and question answering. These models predominant…
An Efficient Fault-Tolerance Scheme for CKKS Computation on CPUs
Jianan Mu, Ge Yu, Tenghui Hua +6
Fully homomorphic encryption (FHE) enables computation on encrypted data, but its long ciphertext dataflow and high-dimensional modular arithmetic make it vulnerable to silent data…
On the Vulnerability of FHE Computation to Silent Data Corruption
Jianan Mu, Ge Yu, Zhaoxuan Kan +6
Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE impl…
The Future of Fully Homomorphic Encryption System: from a Storage I/O Perspective
Lei Chen, Erci Xu, Yiming Sun +8
Fully Homomorphic Encryption (FHE) allows computations to be performed on encrypted data, significantly enhancing user privacy. However, the I/O challenges associated with deployin…