RevealNet: Distributed Traffic Correlation for Attack Attribution on Programmable Networks

TL;DR

RevealNet addresses the scalability limitations of centralized attack attribution by decentralizing flow correlation across P4-programmable switches. It leverages in-network flow-feature extraction and sketch-based representations (e.g., TAM, online Coskun/Nasr sketches) to perform correlation locally, mediated by a lightweight correlation manager. The approach achieves accuracy comparable to centralized systems while drastically reducing bandwidth and compute requirements, with reported bandwidth savings up to 96% in large deployments and robust performance under network perturbations. The work demonstrates the practicality of in-network, decentralized attribution for stepping-stone attacks in high-speed programmable networks, paving the way for scalable, privacy-aware collaboration among operators.

Abstract

Network attackers have increasingly resorted to proxy chains, VPNs, and anonymity networks to conceal their activities. To tackle this issue, past research has explored the applicability of traffic correlation techniques to perform attack attribution, i.e., to identify an attacker's true network location. However, current traffic correlation approaches rely on well-provisioned and centralized systems that ingest flows from multiple network probes to compute correlation scores. Unfortunately, this makes correlation efforts scale poorly for large high-speed networks. In this paper, we propose RevealNet, a decentralized framework for attack attribution that orchestrates a fleet of P4-programmable switches to perform traffic correlation. RevealNet builds on a set of correlation primitives inspired by prior work on computing and comparing flow sketches -- compact summaries of flows' key characteristics -- to enable efficient, distributed, in-network traffic correlation. Our evaluation suggests that RevealNet achieves comparable accuracy to centralized attack attribution systems while significantly reducing both the computational complexity and bandwidth overheads imposed by correlation tasks.

Figures (7)

• Figure 1: Centralized correlation design for attack attribution.
• Figure 2: RevealNet's decentralized correlation architecture.
• Figure 3: RevealNet's dynamic flow identification mechanism.
• Figure 4: bitcoinminer correlation scores for different sketch and TAM configurations (for unperturbed network conditions).
• Figure 5: Length of TAM feature vectors vs. sketches' length.