Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
It exposes critical vulnerabilities in deep learning-based robot localization systems, which are essential for autonomous navigation safety.
This paper proposes a novel adversarial attack framework targeting Product Quantization in visual robot localization systems, using a Lightweight Product Quantization Network (LPQN) to generate subtle perturbations that significantly degrade localization performance in both controlled and real-world environments.
Robot localization systems are critical for autonomous navigation and safety. Adversarial perturbations can mislead these systems, resulting in mislocalization, navigation errors, or unsafe interactions, especially in mission-critical scenarios. This paper investigates the vulnerability of deep learning based localization pipelines to adversarial attacks. We propose a novel framework for generating adversarial queries that specifically target Product Quantization (PQ) in visual localization systems. Our method employs a Lightweight Product Quantization Network (LPQN) to perturb query feature encodings, misleading the retrieval process by returning semantically irrelevant database entries. Adversarial queries are generated via a two-phase procedure: a forward pass that perturbs feature distributions and a backward pass that refines the perturbation through optimization. The lightweight design of LPQN allows the creation of subtle yet highly effective perturbations with minimal computational overhead. Extensive experiments in both controlled and real-world robotic environments demonstrate that our approach substantially degrades PQN performance, exposing critical vulnerabilities in practical applications.