4 papers
HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos +2
Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted user prompts, but current approaches remain prohibitively slow. Ciphertexts nativel…
TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals
Zifan Qu, Vasileios P. Kemerlis, Giuseppe Ateniese +1
Training wide neural networks on sensitive data in untrusted cloud environments requires simultaneously achieving computational efficiency and rigorous privacy guarantees. Sparsifi…
A Secure, Confidential, and Verifiable Decision Support System
Edoardo Marangone, Eugenio Nerio Nemmi, Daniele Friolo +3
Decision support systems are increasingly adopted to automate decision-making processes across industries, organizations, and governments. Decision support demands data privacy, in…
You Don't Need All Attentions: Distributed Dynamic Fine-Tuning for Foundation Models
Shiwei Ding, Lan Zhang, Zhenlin Wang +2
Fine-tuning plays a crucial role in adapting models to downstream tasks with minimal training efforts. However, the rapidly increasing size of foundation models poses a daunting ch…