利用磁导图l3™推进社交网络安全:针对网络威胁的多层防御系统

IF 4.4 2区 计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE
Muhammad Nadeem, Chen Hongsong
{"title":"利用磁导图l3™推进社交网络安全:针对网络威胁的多层防御系统","authors":"Muhammad Nadeem,&nbsp;Chen Hongsong","doi":"10.1016/j.comnet.2025.111375","DOIUrl":null,"url":null,"abstract":"<div><div>Magteon-Turing L3TM is a highly secure and scalable framework specifically designed for real-time social network protection. It integrates advanced large language models (LLMs), including Megatron-Turing NLG, Swarm OpenAI, Langchain, advance Bagging and Ensembling techniques to strengthen threat detection and mitigation capabilities. While previous studies in social network security have largely focused on detecting isolated attack types using dedicated models, such approaches fall short in dynamic environments where networks face multiple, evolving threats. In contrast, the proposed Magteon-Turing L3TM framework is built to detect and defend against a wide spectrum of attacks, eliminating the need for narrowly specialized solutions. This research introduces a novel methodology by integrating Megatron-Turing NLG with multiple learning models, each statistically, probabilistically, and experimentally validated using real-time data from Facebook and Twitter. During evaluation, the framework achieved an accuracy of 98.5 % on Facebook and 98.7 % on Twitter, confirming its reliability and adaptability in real-world conditions. Unlike traditional systems that require retraining for every new threat, Magteon-Turing L3TM can be fine-tuned in response to emerging attacks by dynamically adjusting to specific community and agent-based threat profiles. This makes it the first framework of its kind to unify high-performance LLMs and adaptive learning in a cohesive, real-time security system capable of countering diverse social network vulnerabilities.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"267 ","pages":"Article 111375"},"PeriodicalIF":4.4000,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Advancing social network security with magteon-turing L3TM: A multi-layered defense system against cyber threats\",\"authors\":\"Muhammad Nadeem,&nbsp;Chen Hongsong\",\"doi\":\"10.1016/j.comnet.2025.111375\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Magteon-Turing L3TM is a highly secure and scalable framework specifically designed for real-time social network protection. It integrates advanced large language models (LLMs), including Megatron-Turing NLG, Swarm OpenAI, Langchain, advance Bagging and Ensembling techniques to strengthen threat detection and mitigation capabilities. While previous studies in social network security have largely focused on detecting isolated attack types using dedicated models, such approaches fall short in dynamic environments where networks face multiple, evolving threats. In contrast, the proposed Magteon-Turing L3TM framework is built to detect and defend against a wide spectrum of attacks, eliminating the need for narrowly specialized solutions. This research introduces a novel methodology by integrating Megatron-Turing NLG with multiple learning models, each statistically, probabilistically, and experimentally validated using real-time data from Facebook and Twitter. During evaluation, the framework achieved an accuracy of 98.5 % on Facebook and 98.7 % on Twitter, confirming its reliability and adaptability in real-world conditions. Unlike traditional systems that require retraining for every new threat, Magteon-Turing L3TM can be fine-tuned in response to emerging attacks by dynamically adjusting to specific community and agent-based threat profiles. This makes it the first framework of its kind to unify high-performance LLMs and adaptive learning in a cohesive, real-time security system capable of countering diverse social network vulnerabilities.</div></div>\",\"PeriodicalId\":50637,\"journal\":{\"name\":\"Computer Networks\",\"volume\":\"267 \",\"pages\":\"Article 111375\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2025-05-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Networks\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1389128625003421\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1389128625003421","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0

摘要

Magteon-Turing L3TM是一个高度安全和可扩展的框架,专为实时社交网络保护而设计。它集成了先进的大型语言模型(llm),包括Megatron-Turing NLG, Swarm OpenAI, Langchain,先进的Bagging和Ensembling技术,以加强威胁检测和缓解能力。虽然之前在社交网络安全方面的研究主要集中在使用专用模型检测孤立的攻击类型,但这种方法在网络面临多种不断发展的威胁的动态环境中是不够的。相比之下,所提出的Magteon-Turing l3™框架旨在检测和防御广泛的攻击,从而消除了对狭义专用解决方案的需求。本研究引入了一种新的方法,将Megatron-Turing NLG与多个学习模型相结合,每个模型都使用来自Facebook和Twitter的实时数据进行统计、概率和实验验证。在评估过程中,该框架在Facebook和Twitter上的准确率分别达到98.5%和98.7%,证实了其在现实世界条件下的可靠性和适应性。与传统系统需要针对每个新威胁进行重新培训不同,Magteon-Turing L3TM可以通过动态调整特定社区和基于代理的威胁概况来对新出现的攻击进行微调。这使得它成为同类中第一个将高性能llm和自适应学习统一在一个具有凝聚力的实时安全系统中的框架,能够应对各种社会网络漏洞。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Advancing social network security with magteon-turing L3TM: A multi-layered defense system against cyber threats
Magteon-Turing L3TM is a highly secure and scalable framework specifically designed for real-time social network protection. It integrates advanced large language models (LLMs), including Megatron-Turing NLG, Swarm OpenAI, Langchain, advance Bagging and Ensembling techniques to strengthen threat detection and mitigation capabilities. While previous studies in social network security have largely focused on detecting isolated attack types using dedicated models, such approaches fall short in dynamic environments where networks face multiple, evolving threats. In contrast, the proposed Magteon-Turing L3TM framework is built to detect and defend against a wide spectrum of attacks, eliminating the need for narrowly specialized solutions. This research introduces a novel methodology by integrating Megatron-Turing NLG with multiple learning models, each statistically, probabilistically, and experimentally validated using real-time data from Facebook and Twitter. During evaluation, the framework achieved an accuracy of 98.5 % on Facebook and 98.7 % on Twitter, confirming its reliability and adaptability in real-world conditions. Unlike traditional systems that require retraining for every new threat, Magteon-Turing L3TM can be fine-tuned in response to emerging attacks by dynamically adjusting to specific community and agent-based threat profiles. This makes it the first framework of its kind to unify high-performance LLMs and adaptive learning in a cohesive, real-time security system capable of countering diverse social network vulnerabilities.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Computer Networks
Computer Networks 工程技术-电信学
CiteScore
10.80
自引率
3.60%
发文量
434
审稿时长
8.6 months
期刊介绍: Computer Networks is an international, archival journal providing a publication vehicle for complete coverage of all topics of interest to those involved in the computer communications networking area. The audience includes researchers, managers and operators of networks as well as designers and implementors. The Editorial Board will consider any material for publication that is of interest to those groups.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信