---
title: "When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.03902v1"
permalink: "https://feed.astralor.com/items/itm_66d2de390d3fa12cea2bee03"
published: "2026-08-04T16:29:35.000Z"
score: 78
channel: "ai"
tags: ["Adversarial Path-Inversion","arXiv","Lipschitz Analysis","UAV Tracking","Dynamic Routing","Adversarial Attack"]
---

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

## AI commentary

> This paper is a timely reminder that dynamic routing, built to save computation, may be an unlocked backdoor. For engineers deploying adaptive Transformers on UAVs and edge devices, learning that attackers can push inference onto wrong paths with invisible perturbations is far cheaper than fixing it later. I appreciate how clearly they articulate this mathematical sharp corner — now it's time for the defense side to catch up.

## At a glance

This paper reveals that adaptive Transformer trackers, which use input-dependent dynamic routing to balance accuracy and efficiency, harbor a critical structural flaw: the Lipschitz singularity at layer-skipping decision boundaries makes the local Lipschitz constant unbounded. Tiny input perturbations can be amplified at gating modules, causing dramatic changes in the inference topology. The authors formally characterize this singularity in adaptive tracking architectures and, for the first time, identify it as a directly exploitable new attack surface. They propose the Adversarial Path-Inversion (API) framework, which generates imperceptible perturbations to precisely manipulate gating decisions and force the inference onto altered computational paths. The severe inconsistency between original and inverted paths dismantles the model's representation capability. Extensive experiments on state-of-the-art adaptive trackers demonstrate that API achieves superior perturbation stealthiness, more effective attacks, and faster inference speeds. This work opens a new dimension for security analysis of dynamic tracking networks and provides a theoretical warning for constructing robust adaptive tracking architectures in the future.

## Key points

- Layer-skipping decision boundaries in adaptive Transformer trackers have Lipschitz singularities that amplify tiny input perturbations, causing drastic inference topology changes.
- For the first time, this mathematical discontinuity is identified as an exploitable new attack surface: a topological path space attack surface.
- The Adversarial Path-Inversion (API) framework manipulates gating decisions with imperceptible perturbations, dismantling the model's representation capability.
- Experiments show API achieves superior stealthiness, attack effectiveness, and inference speed on state-of-the-art adaptive trackers.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_66d2de390d3fa12cea2bee03