When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking

2026-08-04

AI Summary

This work reveals that the dynamic routing mechanism in adaptive drone tracking models introduces Lipschitz singularities at discrete layer-skipping boundaries, rendering computational paths highly sensitive to minute input perturbations. To address this vulnerability, the paper proposes the Adversarial Path Inversion (API) framework, which for the first time identifies Lipschitz discontinuities in dynamic routing as a novel attack surface. API leverages imperceptible perturbations to precisely manipulate inference paths, thereby degrading the model’s representational capacity. Experiments demonstrate that API achieves high stealthiness and strong attack efficacy across mainstream adaptive Transformer-based trackers, while simultaneously accelerating inference and significantly impairing tracking performance. This study establishes a new paradigm for security analysis in dynamic neural networks.

Abstract

Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficiency. Adaptive Transformer Trackers, which leverage an input-dependent dynamic routing architecture, have emerged as a representative solution to this challenge. However, we reveal that behind this computation-on-demand flexibility hides a critical structural flaw: the Lipschitz singularity of computational path decisions, which has an unbounded local Lipschitz constant at discrete layer-skipping decision boundaries. This mathematical discontinuity renders adaptive tracking networks inherently unstable: tiny input perturbations can be amplified at the gating modules, causing dramatic changes in the inference topology. We formally characterize this singularity in the context of adaptive tracking architectures and, for the first time, identify it as a directly exploitable new attack surface. This insight reveals a previously overlooked and highly vulnerable topological path space attack surface. Based on this, we propose the Adversarial Path-Inversion (API) framework. API generates imperceptible perturbations to precisely manipulate the gating decisions, forcing the inference onto altered computational paths. The severe inconsistency between the original and the inverted paths dismantles the representation capability of the model. Extensive experiments on state-of-the-art adaptive trackers demonstrate that API achieves superior perturbation stealthiness, more effective attack, and faster inference speeds. This work opens a new dimension for the security analysis of dynamic tracking networks and provides a theoretical warning for constructing robust adaptive tracking architectures in the future.

Problem

• dynamic routing
• Lipschitz singularity
• adaptive tracking
• UAV tracking
• adversarial vulnerability

Innovation

• dynamic routing
• Lipschitz singularity
• adversarial attack
• adaptive tracking
• path inversion