RoTO: Robust Topology Obfuscation Against Tomography Inference Attacks

TL;DR

RoTO is a novel topology obfuscation method that robustly defends against tomography inference attacks by modeling uncertainties and using adversarial training, outperforming existing defenses in accuracy and robustness.

Contribution

RoTO introduces a distributional approach and adversarial training to enhance topology obfuscation without relying on perfect probe control or fixed attacker models.

Findings

RoTO achieves 34% better structural similarity reduction.

RoTO improves link distance concealment by 42.6%.

RoTO outperforms existing methods in robustness and effectiveness.

Abstract

Tomography inference attacks aim to reconstruct network topology by analyzing end-to-end probe delays. Existing defenses mitigate these attacks by manipulating probe delays to mislead inference, but rely on two strong assumptions: (i) probe packets can be perfectly detected and altered, and (ii) attackers use known, fixed inference algorithms. These assumptions often break in practice, leading to degraded defense performance under detection errors or adaptive adversaries. We present RoTO, a robust topology obfuscation scheme that eliminates both assumptions by modeling uncertainty in attacker-observed delays through a distributional formulation. RoTO casts the defense objective as a min-max optimization problem that maximizes expected topological distortion across this uncertainty set, without relying on perfect probe control or specific attacker models. To approximate attacker behavior, RoTO leverages graph neural networks for inference simulation and adversarial training. We also derive an upper bound on attacker success probability, and demonstrate that our approach enhances topology obfuscation performance through the optimization of this upper bound. Experimental results show that RoTO outperforms existing defense methods, achieving average improvements of 34% in structural similarity and 42.6% in link distance while maintaining strong robustness and concealment capabilities.