Hybrid Attention-GAN Framework for Secure Data Encryption and Decryption: Leveraging Transformer-based Attention Mechanisms and Adversarial Learning

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: s, Sangheethaa
Format: Recurso digital
Published: Zenodo 2024
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901608459141120
author s, Sangheethaa
author_facet s, Sangheethaa
contents <p>This paper introduces a novel Hybrid Attention-GAN Framework that integrates transformer-based attention mechanisms with generative adversarial learning to perform secure data encryption and decryption. The proposed model employs a Transformer encoder to capture complex dependencies in plaintext and a GAN generator to produce highly obfuscated ciphertext that closely resembles random noise. On the decryption side, a self-supervised Transformer decoder reconstructs the original data without needing explicit plaintext-ciphertext pairs, enhancing both adaptability and security. The key contributions include:</p> <ul> <li> <p>The first dual-phase encryption-decryption architecture combining Transformers and GANs.</p> </li> <li> <p>Use of self-supervised learning for decryption, significantly improving accuracy while reducing training overhead.</p> </li> </ul>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15193574
institution Zenodo
language
publishDate 2024
publisher Zenodo
record_format zenodo
spellingShingle Hybrid Attention-GAN Framework for Secure Data Encryption and Decryption: Leveraging Transformer-based Attention Mechanisms and Adversarial Learning
s, Sangheethaa
<p>This paper introduces a novel Hybrid Attention-GAN Framework that integrates transformer-based attention mechanisms with generative adversarial learning to perform secure data encryption and decryption. The proposed model employs a Transformer encoder to capture complex dependencies in plaintext and a GAN generator to produce highly obfuscated ciphertext that closely resembles random noise. On the decryption side, a self-supervised Transformer decoder reconstructs the original data without needing explicit plaintext-ciphertext pairs, enhancing both adaptability and security. The key contributions include:</p> <ul> <li> <p>The first dual-phase encryption-decryption architecture combining Transformers and GANs.</p> </li> <li> <p>Use of self-supervised learning for decryption, significantly improving accuracy while reducing training overhead.</p> </li> </ul>
title Hybrid Attention-GAN Framework for Secure Data Encryption and Decryption: Leveraging Transformer-based Attention Mechanisms and Adversarial Learning
url https://doi.org/10.5281/zenodo.15193574