On Adversarial Attacks In Acoustic Localization

TMLR Paper6532 Authors

Abstract:

Multi-rotor aerial vehicles (drones) are increasingly deployed across diverse domains, where
accurate navigation is critical. The limitations of vision-based methods under poor lighting
and occlusions have driven growing interest in acoustic sensing as an alternative. However,
the security of acoustic-based localization has not been examined. Adversarial attacks pose
a serious threat, potentially leading to mission-critical failures and safety risks. While prior
research has explored adversarial attacks on vision-based systems, no work has addressed
the acoustic setting. In this paper, we present the first comprehensive study of adversarial
robustness in acoustic drone localization. We formulate white-box projected gradient descent (PGD) attacks from an external sound source and show their significant impact on
localization accuracy. Furthermore, we propose a novel defense algorithm based on rotor
phase modulation, capable of effectively recovering clean signals and mitigating adversarial
degradation. Our results highlight both the vulnerability of acoustic localization and the
potential for robust defense strategies.

Submission Type: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: Added discussion of future work, including multi-source attacks and real-time adversarial adaptations (to address comments by reviewer Nwh5). Changed figure references and captions, and fixed notation error in 3.3.4 (comments from reviewer TQsR).

Assigned Action Editor: ~Tongliang_Liu1

Submission Number: 6532