@article{ART003277357},
author={Kyung-Yeob Park and Hyun-Soo Kim and Chang-Jun Choi and Shin DongMyung},
title={LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2025},
volume={21},
number={4},
pages={99-114}
TY - JOUR
AU - Kyung-Yeob Park
AU - Hyun-Soo Kim
AU - Chang-Jun Choi
AU - Shin DongMyung
TI - LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique
JO - Journal of Software Assessment and Valuation
PY - 2025
VL - 21
IS - 4
PB - Korea Software Assessment and Valuation Society
SP - 99
EP - 114
SN - 2092-8114
AB - Due to the proliferation of illegal video streaming services and illicit webtoon and publication sharing sites, secure sharing and access control of investigative documents and evidence in international joint investigations have become increasingly critical. This paper proposes a condition-hiding proxy re-encryption scheme that combines a Large Language Model (LLM) embedding-based attribute recommendation method with a Secret Sharing Scheme (SSS) to enable document-centric access control in the absence of explicit organizational policy tables. We construct a document-attribute label dataset from Korean PDF investigation documents, design a model that recommends top-K attributes in a shared embedding space, and embed a hashed condition scalar in the ciphertext exponent while distributing the server secret via Shamir’s scheme, thereby evaluating whether the proposed protocol satisfies security and availability requirements under realistic operational constraints and threat models and confirming its applicability to international cooperative investigation scenarios.
KW - Large Language Model;Artificial Intelligence;Recommendation System;Cryptography;;Secret Sharing Scheme;Proxy Re-Encryption
DO -
UR -
ER -
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi and Shin DongMyung. (2025). LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique. Journal of Software Assessment and Valuation, 21(4), 99-114.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi and Shin DongMyung. 2025, "LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique", Journal of Software Assessment and Valuation, vol.21, no.4 pp.99-114.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi, Shin DongMyung "LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique" Journal of Software Assessment and Valuation 21.4 pp.99-114 (2025) : 99.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi, Shin DongMyung. LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique. 2025; 21(4), 99-114.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi and Shin DongMyung. "LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique" Journal of Software Assessment and Valuation 21, no.4 (2025) : 99-114.
Kyung-Yeob Park; Hyun-Soo Kim; Chang-Jun Choi; Shin DongMyung. LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique. Journal of Software Assessment and Valuation, 21(4), 99-114.
Kyung-Yeob Park; Hyun-Soo Kim; Chang-Jun Choi; Shin DongMyung. LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique. Journal of Software Assessment and Valuation. 2025; 21(4) 99-114.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi, Shin DongMyung. LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique. 2025; 21(4), 99-114.
Kyung-Yeob Park, Hyun-Soo Kim, Chang-Jun Choi and Shin DongMyung. "LLM Embedding-based Attribute Recommendation and SSS Combined Condition Hiding Proxy Re-encryption Technique" Journal of Software Assessment and Valuation 21, no.4 (2025) : 99-114.
