Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Chunlong, He, Jialing, Guo, Shangwei, Wang, Jiacheng, Zhang, Shudong, Zhang, Tianwei, Xiang, Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915312446734336
author Xie, Chunlong
He, Jialing
Guo, Shangwei
Wang, Jiacheng
Zhang, Shudong
Zhang, Tianwei
Xiang, Tao
author_facet Xie, Chunlong
He, Jialing
Guo, Shangwei
Wang, Jiacheng
Zhang, Shudong
Zhang, Tianwei
Xiang, Tao
contents We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attacks fail to address service computing contexts, where reliability and quality-of-service (QoS) are paramount. We utilize AdvOF to investigate and explore the impact of adversarial environments on the VLM-based perception module of VLN agents. In particular, AdvOF first precisely aggregates and aligns the victim object positions in both 2D and 3D space, defining and rendering adversarial objects. Then, we collaboratively optimize the adversarial object with regularization between the adversarial and victim object across physical properties and VLM perceptions. Through assigning importance weights to varying views, the optimization is processed stably and multi-viewedly by iterative fusions from local updates and justifications. Our extensive evaluations demonstrate AdvOF can effectively degrade agent performance under adversarial conditions while maintaining minimal interference with normal navigation tasks. This work advances the understanding of service security in VLM-powered navigation systems, providing computational foundations for robust service composition in physical-world deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23266
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
Xie, Chunlong
He, Jialing
Guo, Shangwei
Wang, Jiacheng
Zhang, Shudong
Zhang, Tianwei
Xiang, Tao
Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attacks fail to address service computing contexts, where reliability and quality-of-service (QoS) are paramount. We utilize AdvOF to investigate and explore the impact of adversarial environments on the VLM-based perception module of VLN agents. In particular, AdvOF first precisely aggregates and aligns the victim object positions in both 2D and 3D space, defining and rendering adversarial objects. Then, we collaboratively optimize the adversarial object with regularization between the adversarial and victim object across physical properties and VLM perceptions. Through assigning importance weights to varying views, the optimization is processed stably and multi-viewedly by iterative fusions from local updates and justifications. Our extensive evaluations demonstrate AdvOF can effectively degrade agent performance under adversarial conditions while maintaining minimal interference with normal navigation tasks. This work advances the understanding of service security in VLM-powered navigation systems, providing computational foundations for robust service composition in physical-world deployments.
title Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
topic Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.23266