LEAP: A Lightweight, Explainable, and Programmable Framework for Traffic-Aware Routing in Encrypted SDN Environments
编号:123 访问权限:仅限参会人 更新:2025-12-23 13:12:28 浏览:105次 拓展类型2

报告开始:2025年12月30日 17:00(Asia/Amman)

报告时间:15min

所在会场:[S1] Track 1: Mobile computing, communications, 5G and beyond [S1-2] Track 1: Mobile computing, communications, 5G and beyond

视频 无权播放 演示文件

提示:该报告下的文件权限为仅限参会人,您尚未登录,暂时无法查看。

摘要
This paper addresses the critical challenge of traffic-aware routing in modern Software-Defined Networking (SDN) environments, which are increasingly defined by the dual pressures of pervasive traffic encryption and the demand for real-time, adaptive network control. The widespread adoption of protocols like TLS 1.3 and QUIC, particularly with privacy-enhancing features such as Encrypted Client Hello (ECH), has rendered traditional visibility tools obsolete, hindering intelligent network management. Concurrently, controller-centric machine learning approaches introduce significant performance bottlenecks and lack the transparency required for operator trust. To overcome these limitations, this work introduces the Lightweight, Explainable, and Programmable (LEAP) framework. LEAP presents a novel, synergistic architecture that integrates a Deep Reinforcement Learning (DRL) agent in the control plane for adaptive, high-level routing policy generation; a highly efficient, lightweight Gradient Boosting Decision Tree (GBDT) classifier, compressed via knowledge distillation and deployed in P4- programmable data planes for line-rate traffic identification; and a dedicated Explainable AI (XAI) module to provide human- interpretable justifications for both classification and routing decisions. Through extensive emulation in a realistic network environment using modern, encrypted traffic datasets, the LEAP framework demonstrates significant improvements in network throughput and end-to-end latency compared to state-of-the-art baselines, establishing a new paradigm for efficient, transparent, and autonomous network management.
 
关键词
Software-Defined Networking, Traffic Classification, Deep Reinforcement Learning, P4, Explainable AI, Encrypted Traffic, QUIC
报告人
Shaik Luqman Sajid
Assistant Professor Amrita School of Computing Amrita Vishwa Vidyapeetham Amaravati, 522503, Andhra Pradesh, India

稿件作者
Shaik Luqman Sajid Amrita School of Computing Amrita Vishwa Vidyapeetham Amaravati, 522503, Andhra Pradesh, India
Anto Lourdu Xavier Raj Arockia Selvarathinam USA;Department of Data Science and Analytics College of Computing Grand Valley State University Michigan
Ayman Amer Faculty of Engineering; Jordan; Zarqa Univeristy
Mohamed Hafez INTI-IU-University;Shinawatra University
Mohammad Tahidul Islam Australia;School of IT and Engineering Melbourne Institute of Technology Melbourne
Yogesh Kumar India; Gandhinagar;Department of CSE; School of Technology; Pandit Deendayal Energy University
Muhammad Umair Manzoor Australia;School of Engineering RMIT University; Melbourne
Muhammad Fazal Ijaz Australia;Torrens University
发表评论
验证码 看不清楚,更换一张
全部评论
重要日期
  • 会议日期

    12月29日

    2025

    12月31日

    2025

  • 12月30日 2025

    报告提交截止日期

  • 02月10日 2026

    初稿截稿日期

  • 02月10日 2026

    注册截止日期

主办单位
国际科学联合会
承办单位
扎尔卡大学
历届会议
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询