arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.06140cs.LGcs.CVcs.NI
收藏

使用深度学习估计 QUIC 中 HTTP/3 响应的数量

Estimating the Number of HTTP/3 Responses in QUIC Using Deep Learning

Technion Israel Institute of Technology(技术学院以色列理工学院)

Barak Gahtan, Robert J. Shahla, Reuven Cohen, Alex M. Bronstein

AI总结:

本文提出一种基于深度学习的方法,将 QUIC 连接轨迹转换为图像序列并利用定制损失函数预测 HTTP/3 响应数量,在超 700 万张图像上实现高达 97% 的准确率,助力负载均衡与泛洪攻击检测。

摘要:

QUIC 是一种新型且日益普及的传输协议,通过提供增强的安全性、性能和流多路复用来改进 TCP。然而,这些特性也给需要监控和分析 Web 流量的网络中间盒带来了挑战。本文提出了一种新方法,供观察者估计给定 QUIC 连接中 HTTP/3 响应的数量。该估计揭示了服务器行为、客户端与服务器交互及数据传输效率,对设计负载均衡解决方案和检测 HTTP/3 泛洪攻击等各种应用至关重要。所提方案将 QUIC 连接轨迹转换为图像序列,并使用机器学习(ML)模型,在定制损失函数的引导下预测响应计数。在四个月内从 44,000 个网站收集的 100,000 条轨迹衍生出的超过 700 万张图像上进行评估,在已知和未知服务器设置中均实现了高达 97% 的准确率,在先前未见过的完整 QUIC 轨迹上实现了 92% 的准确率。

英文摘要:

QUIC, a new and increasingly used transport protocol, enhances TCP by offering improved security, performance, and stream multiplexing. These features, however, also impose challenges for network middle-boxes that need to monitor and analyze web traffic. This paper proposes a novel method to estimate the number of HTTP/3 responses in a given QUIC connection by an observer. This estimation reveals server behavior, client-server interactions, and data transmission efficiency, which is crucial for various applications such as designing a load balancing solution and detecting HTTP/3 flood attacks. The proposed scheme transforms QUIC connection traces into image sequences and uses machine learning (ML) models, guided by a tailored loss function, to predict response counts. Evaluations on more than seven million images-derived from 100,000 traces collected across 44,000 websites over four months-achieve up to 97% accuracy in both known and unknown server settings and 92% accuracy on previously unseen complete QUIC traces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑