Skip to content

Transformer-based language models and homomorphic encryption: An intersection with bert-tiny

Authors: Lorenzo Rovida; Alberto Leporati
Year: 2024
Venue: Proceedings of the 10th ACM International Workshop on Security and Privacy Analytics

status: auto

Links: DOI

System card: RL (Rovida & Leporati)

Group 0. CKKS LLM frameworks surveyed in the SoK
Family CKKS · Model-modifying (N-MOD)
Arithmetic Approximate real (CKKS)
Interaction non-interactive FHE
Model scale BERT-Tiny
Library OpenFHE
Hardware Apple M1 Pro CPU
Packing L-ROW
Latency ~672 s unamortized (32 tokens)
Open source yes
Status Foundational
Relation to the SoK Early open-source CKKS BERT-Tiny with precomputed LayerNorm statistics.
Note Educational baseline; accuracy loss >1.5% / retraining needed.
Code https://github.com/narger-ef/EncryptedTransformer
Systems page RL (Rovida & Leporati)

SoK reference [11]

L. Rovida and A. Leporati, “Transformer-based language models and homomorphic encryption: An intersection with bert-tiny,” in Proceedings of the 10th ACM International Workshop on Security and Privacy Analytics, ser. IWSPA ’24. New York, NY, USA: Association for Computing Machinery, 2024, p. 3–13. [Online]. Available: https://doi.org/10.1145/3643651.3659893

Listed on the reference page of the site.

Files

No local PDF in the archive.


Database key: transformer-based-language-models-and-homomorphic-encryption-an · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set transformer-based-language-models-and-homomorphic-encryption-an COLUMN VALUE