Skip to content

Pritran: Privacy-preserving inference for transformer-based language models under fully homomorphic encryption

Authors: Yuechen Mu; Guangli Li; Shiping Chen; Jingling Xue
Year: 2026
Venue: 2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)

status: auto

Links: DOI

System card: PRITRAN

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, BERT-Mini
Library OpenFHE
Hardware 64-core CPU
Packing L-ROW
Latency 398 s (Tiny) / ~2000 s (Mini) unamortized
Open source no
Status Niche
Relation to the SoK Row packing with precomputed LayerNorm statistics.
Note No utility metric reported.
Systems page PRITRAN

SoK reference [12]

Y. Mu, G. Li, S. Chen, and J. Xue, “Pritran: Privacy-preserving inference for transformer-based language models under fully homomorphic encryption,” in 2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO), 2026, pp. 57–69.

Listed on the reference page of the site.

Files

No local PDF in the archive.


Database key: pritran-privacy-preserving-inference-for-transformer-based-language · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set pritran-privacy-preserving-inference-for-transformer-based-language COLUMN VALUE