Skip to content

PREMAL_Bench paper database

A browsable view of db/premal.sqlite: every paper in the local archive (papers/), the curated scheme and system tables of the CKKS Alternatives Atlas, and the details extracted from the PDFs.

Papers 311 (276 with a local PDF)
PDF files 361 files, 278 distinct documents, 83 byte-identical copies
Abstracts / summaries 271 / 276
Extracted detail rows 6115
Last scan / enrich / tag 2026-11-05 / 2026-11-05 / 2026-11-05

Collections

Collection Papers Folder
The SoK 1 papers/
SoK references 88 papers/references/sok-references/
Systems catalogue 118 papers/references/catalogue/
Scheme papers 96 papers/references/schemes/
PPML with FHE (PREMAL collection) 51 papers/references/ppml/
Misfiled downloads 2 papers/references/misfiled/

Browse

Recently added

Paper Authors Year Venue Type Links
Benaloh's Dense Probabilistic Encryption Revisited Fousse et al. 2010 arXiv preprint theory arXiv:1008.2991
GPT-4 System Card OpenAI 2023 OpenAI technical report other link
SoK: Private LLM Inference using Approximate Homomorphic Encryption Al Badawi et al. 2026 SoK paper (IACR ePrint 2026/935) system ePrint 2026/935
THOR: Secure transformer inference with homomorphic encryption Moon et al. 2025 IACR ePrint / CCS 2025 system ePrint 2024/1881
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption Castro et al. 2024 NeurIPS 2024 workshop; ICML 2025 (EncryptedLLM) system link
Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache Yu et al. 2026 arXiv 2602.11470 system arXiv:2602.11470
A scalable multi-GPU framework for encrypted large-model inference Jayashankar et al. 2025 arXiv 2512.11269 system DOI · arXiv:2512.11269
Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B (v1: Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B) Park et al. 2026 arXiv 2601.18511 system arXiv:2601.18511
ARION: Attention-optimized transformer inference on encrypted data Yang et al. 2025 IACR ePrint 2025/2271 system ePrint 2025/2271
ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference Guzelhan et al. 2026 IACR ePrint 2026/198 system ePrint 2026/198 · Semantic Scholar
TRICYCLE: Private transformer inference with tricyclic encodings Lim et al. 2025 IACR ePrint 2025/1200 system ePrint 2025/1200
Encryption-friendly LLM architecture Rho et al. 2025 ICLR 2025 system arXiv:2410.02486
Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity Gao et al. 2026 IACR ePrint 2026/046 system ePrint 2026/46 · link
Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption Park et al. 2025 ACL 2025 (long) system link
MOAI: Module-optimizing architecture for non-interactive secure transformer inference Zhang et al. 2026 ICLR 2026; IACR ePrint 2025/991 system ePrint 2025/991

Working with the database

See How to maintain, the schema and the query cookbook. Quick start:

sqlite3 db/premal.sqlite "SELECT key, year, title FROM papers WHERE paper_type='system' ORDER BY year DESC LIMIT 10"
python3 tools/paperdb.py search "softmax approximation"