Saved in:
Bibliographic Details
Main Authors: Xiong, Zikang, Jagannathan, Suresh
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.18256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917636723441664
author Xiong, Zikang
Jagannathan, Suresh
author_facet Xiong, Zikang
Jagannathan, Suresh
contents Data-driven neural path planners are attracting increasing interest in the robotics community. However, their neural network components typically come as black boxes, obscuring their underlying decision-making processes. Their black-box nature exposes them to the risk of being compromised via the insertion of hidden malicious behaviors. For example, an attacker may hide behaviors that, when triggered, hijack a delivery robot by guiding it to a specific (albeit wrong) destination, trapping it in a predefined region, or inducing unnecessary energy expenditure by causing the robot to repeatedly circle a region. In this paper, we propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners. Our approach provides a concise but flexible way to define these behaviors, and we show that hidden behaviors can be triggered by slight perturbations (e.g., inserting a tiny unnoticeable object), that can nonetheless significantly compromise their integrity. We also discuss potential techniques to identify these backdoors aimed at alleviating such risks. We demonstrate our approach on both sampling-based and search-based neural path planners.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18256
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Manipulating Neural Path Planners via Slight Perturbations
Xiong, Zikang
Jagannathan, Suresh
Robotics
Artificial Intelligence
Data-driven neural path planners are attracting increasing interest in the robotics community. However, their neural network components typically come as black boxes, obscuring their underlying decision-making processes. Their black-box nature exposes them to the risk of being compromised via the insertion of hidden malicious behaviors. For example, an attacker may hide behaviors that, when triggered, hijack a delivery robot by guiding it to a specific (albeit wrong) destination, trapping it in a predefined region, or inducing unnecessary energy expenditure by causing the robot to repeatedly circle a region. In this paper, we propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners. Our approach provides a concise but flexible way to define these behaviors, and we show that hidden behaviors can be triggered by slight perturbations (e.g., inserting a tiny unnoticeable object), that can nonetheless significantly compromise their integrity. We also discuss potential techniques to identify these backdoors aimed at alleviating such risks. We demonstrate our approach on both sampling-based and search-based neural path planners.
title Manipulating Neural Path Planners via Slight Perturbations
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2403.18256