On Adversarial Attacks In Acoustic Drone Localization

2025-02-27

AI Summary

Adversarial attacks pose a critical threat to acoustic localization systems for micro aerial vehicles (MAVs) operating in uncontrolled environments—a domain largely overlooked by prior research, which has predominantly focused on vision-based navigation. Method: This paper presents the first systematic evaluation of Projected Gradient Descent (PGD) attacks on acoustic localization robustness and proposes a novel adversarial perturbation recovery algorithm. The method integrates acoustic signal processing, deep learning–based localization models, and PGD attack generation mechanisms through perturbation modeling and signal reconstruction optimization. Contribution/Results: Experimental results demonstrate that the proposed algorithm reduces the average localization error induced by PGD attacks by over 65% under standard acoustic localization tasks, significantly enhancing system resilience and security. This work bridges a key gap in trustworthy acoustic navigation, providing both a principled methodology and empirical validation for secure deployment of acoustic localization in MAVs.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Multi-rotor aerial autonomous vehicles (MAVs, more widely known as"drones") have been generating increased interest in recent years due to their growing applicability in a vast and diverse range of fields (e.g., agriculture, commercial delivery, search and rescue). The sensitivity of visual-based methods to lighting conditions and occlusions had prompted growing study of navigation reliant on other modalities, such as acoustic sensing. A major concern in using drones in scale for tasks in non-controlled environments is the potential threat of adversarial attacks over their navigational systems, exposing users to mission-critical failures, security breaches, and compromised safety outcomes that can endanger operators and bystanders. While previous work shows impressive progress in acoustic-based drone localization, prior research in adversarial attacks over drone navigation only addresses visual sensing-based systems. In this work, we aim to compensate for this gap by supplying a comprehensive analysis of the effect of PGD adversarial attacks over acoustic drone localization. We furthermore develop an algorithm for adversarial perturbation recovery, capable of markedly diminishing the affect of such attacks in our setting. The code for reproducing all experiments will be released upon publication.

Problem

• Analyzing adversarial attacks on acoustic drone localization
• Developing recovery algorithm for adversarial perturbations
• Addressing security gaps in acoustic-based drone navigation

Innovation

• Adversarial attack analysis
• Acoustic drone localization
• Adversarial perturbation recovery