EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Donghe, Li, Zuchen, Yang, Ye, Sun, Li, An, Dou, Yang, Qingyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913766135824384
author Li, Donghe
Li, Zuchen
Yang, Ye
Sun, Li
An, Dou
Yang, Qingyu
author_facet Li, Donghe
Li, Zuchen
Yang, Ye
Sun, Li
An, Dou
Yang, Qingyu
contents Communication encryption is crucial in computer technology, but existing algorithms struggle with balancing cost and security. We propose EncGPT, a multi-agent framework using large language models (LLM). It includes rule, encryption, and decryption agents that generate encryption rules and apply them dynamically. This approach addresses gaps in LLM-based multi-agent systems for communication security. We tested GPT-4o's rule generation and implemented a substitution encryption workflow with homomorphism preservation, achieving an average execution time of 15.99 seconds.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms
Li, Donghe
Li, Zuchen
Yang, Ye
Sun, Li
An, Dou
Yang, Qingyu
Cryptography and Security
Multiagent Systems
Communication encryption is crucial in computer technology, but existing algorithms struggle with balancing cost and security. We propose EncGPT, a multi-agent framework using large language models (LLM). It includes rule, encryption, and decryption agents that generate encryption rules and apply them dynamically. This approach addresses gaps in LLM-based multi-agent systems for communication security. We tested GPT-4o's rule generation and implemented a substitution encryption workflow with homomorphism preservation, achieving an average execution time of 15.99 seconds.
title EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms
topic Cryptography and Security
Multiagent Systems
url https://arxiv.org/abs/2503.23138