{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T03:43:45Z","timestamp":1768880625449,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802618","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"13845-13852","source":"Crossref","is-referenced-by-count":5,"title":["Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems"],"prefix":"10.1109","author":[{"given":"Chashi Mahiul","family":"Islam","sequence":"first","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida,USA,32306"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaeke","family":"Salman","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida,USA,32306"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Montasir","family":"Shams","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida,USA,32306"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida,USA,32306"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piyush","family":"Kumar","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida,USA,32306"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01282"},{"key":"ref3","article-title":"On the road with gpt-4v(ision): Early explorations of visual-language model on autonomous driving","author":"Wen","year":"2023"},{"key":"ref4","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2022"},{"key":"ref5","article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Representations","author":"Goodfellow"},{"key":"ref6","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"ref8","article-title":"Understanding and improving robustness of vision transformers through patch-based negative augmentation","author":"Qin","year":"2023"},{"key":"ref9","article-title":"Intriguing equivalence structures of the embedding space of vision transformers","author":"Salman","year":"2024"},{"key":"ref10","article-title":"Intriguing differences between zero-shot and systematic evaluations of vision-language transformer models","author":"Salman","year":"2024"},{"key":"ref11","article-title":"Unaligning everything: Or aligning any text to any image in multimodal models","author":"Salman","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3473140"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3526024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3239837"},{"key":"ref18","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref19","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref20","article-title":"Can an embodied agent find your \u201dcat-shaped mug\"? llm-guided exploration for zero-shot object navigation","author":"Dorbala","year":"2023"},{"key":"ref21","article-title":"Vint: A foundation model for visual navigation","author":"Shah","year":"2023"},{"key":"ref22","article-title":"Transferring foundation models for generalizable robotic manipulation","author":"Yang","year":"2023"},{"key":"ref23","article-title":"How secure are large language models (llms) for navigation in urban environments?","author":"Wen","year":"2024"},{"key":"ref24","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref25","article-title":"Large language models can be easily distracted by irrelevant context","author":"Shi","year":"2023"},{"key":"ref26","article-title":"Visual adversarial examples jailbreak aligned large language models","author":"Qi","year":"2023"},{"key":"ref27","article-title":"Chasing ghosts: Instruction following as bayesian state tracking","author":"Anderson","year":"2019"},{"key":"ref28","article-title":"Topological planning with transformers for vision-and-language navigation","author":"Chen","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485935"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1145\/3460120.3485377","volume-title":"Can we use arbitrary objects to attack lidar perception in autonomous driving?","author":"Zhu","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2017.20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3216291"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802618.pdf?arnumber=10802618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:31Z","timestamp":1735196491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802618","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}