Black-box Adversarial Attacks on CNN-based SLAM Algorithms

TL;DR

This paper investigates the vulnerability of CNN-based SLAM algorithms to black-box adversarial attacks, demonstrating that moderate perturbations can cause significant tracking failures and highlighting the severe impact of depth attacks.

Contribution

It is the first comprehensive study on black-box adversarial attacks targeting CNN-based feature detectors within SLAM systems.

Findings

Attacks of moderate scale cause up to 76% tracking failure.

Attacking depth inputs has a more catastrophic impact than RGB.

Black-box adversarial perturbations can significantly disrupt SLAM performance.

Abstract

Continuous advancements in deep learning have led to significant progress in feature detection, resulting in enhanced accuracy in tasks like Simultaneous Localization and Mapping (SLAM). Nevertheless, the vulnerability of deep neural networks to adversarial attacks remains a challenge for their reliable deployment in applications, such as navigation of autonomous agents. Even though CNN-based SLAM algorithms are a growing area of research there is a notable absence of a comprehensive presentation and examination of adversarial attacks targeting CNN-based feature detectors, as part of a SLAM system. Our work introduces black-box adversarial perturbations applied to the RGB images fed into the GCN-SLAM algorithm. Our findings on the TUM dataset [30] reveal that even attacks of moderate scale can lead to tracking failure in as many as 76% of the frames. Moreover, our experiments highlight the catastrophic impact of attacking depth instead of RGB input images on the SLAM system.