{"year":"2023","related_material":{"link":[{"relation":"software","url":"https://github.com/patchadversarialattacks/patchadversarialattacks"}]},"scopus_import":"1","_id":"18218","article_processing_charge":"No","date_updated":"2024-10-09T12:13:36Z","title":"Physical passive patch adversarial attacks on visual odometry systems","external_id":{"arxiv":["2207.05729"]},"abstract":[{"lang":"eng","text":"Deep neural networks are known to be susceptible to adversarial perturbations – small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model’s output on a set of inputs. Universal perturbations present a more realistic case of adversarial attacks, as awareness of the model’s exact input is not required. In addition, the universal attack setting raises the subject of generalization to unseen data, where given a set of inputs, the universal perturbations aim to alter the model’s output on out-of-sample data. In this work, we study physical passive patch adversarial attacks on visual odometry-based autonomous navigation systems. A visual odometry system aims to infer the relative camera motion between two corresponding viewpoints, and is frequently used by vision-based autonomous navigation systems to estimate their state. For such navigation systems, a patch adversarial perturbation poses a severe security issue, as it can be used to mislead a system onto some collision course. To the best of our knowledge, we show for the first time that the error margin of a visual odometry model can be significantly increased by deploying patch adversarial attacks in the scene. We provide evaluation on synthetic closed-loop drone navigation data and demonstrate that a comparable vulnerability exists in real data. A reference implementation of the proposed method and the reported experiments is provided at https://github.com/patchadversarialattacks/patchadversarialattacks."}],"language":[{"iso":"eng"}],"author":[{"full_name":"Nemcovsky, Yaniv","first_name":"Yaniv","last_name":"Nemcovsky"},{"last_name":"Jacoby","first_name":"Matan","full_name":"Jacoby, Matan"},{"id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","full_name":"Bronstein, Alexander","last_name":"Bronstein","orcid":"0000-0001-9699-8730","first_name":"Alexander"},{"full_name":"Baskin, Chaim","first_name":"Chaim","last_name":"Baskin"}],"publication_status":"published","citation":{"short":"Y. Nemcovsky, M. Jacoby, A.M. Bronstein, C. Baskin, in:, 16th Asian Conference on Computer Vision, Springer Nature, 2023, pp. 518–534.","chicago":"Nemcovsky, Yaniv, Matan Jacoby, Alex M. Bronstein, and Chaim Baskin. “Physical Passive Patch Adversarial Attacks on Visual Odometry Systems.” In <i>16th Asian Conference on Computer Vision</i>, 13847:518–34. Springer Nature, 2023. <a href=\"https://doi.org/10.1007/978-3-031-26293-7_31\">https://doi.org/10.1007/978-3-031-26293-7_31</a>.","ama":"Nemcovsky Y, Jacoby M, Bronstein AM, Baskin C. Physical passive patch adversarial attacks on visual odometry systems. In: <i>16th Asian Conference on Computer Vision</i>. Vol 13847. Springer Nature; 2023:518-534. doi:<a href=\"https://doi.org/10.1007/978-3-031-26293-7_31\">10.1007/978-3-031-26293-7_31</a>","apa":"Nemcovsky, Y., Jacoby, M., Bronstein, A. M., &#38; Baskin, C. (2023). Physical passive patch adversarial attacks on visual odometry systems. In <i>16th Asian Conference on Computer Vision</i> (Vol. 13847, pp. 518–534). Macao, China: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-031-26293-7_31\">https://doi.org/10.1007/978-3-031-26293-7_31</a>","mla":"Nemcovsky, Yaniv, et al. “Physical Passive Patch Adversarial Attacks on Visual Odometry Systems.” <i>16th Asian Conference on Computer Vision</i>, vol. 13847, Springer Nature, 2023, pp. 518–34, doi:<a href=\"https://doi.org/10.1007/978-3-031-26293-7_31\">10.1007/978-3-031-26293-7_31</a>.","ista":"Nemcovsky Y, Jacoby M, Bronstein AM, Baskin C. 2023. Physical passive patch adversarial attacks on visual odometry systems. 16th Asian Conference on Computer Vision. ACCV: Asian Conference on Computer Vision, LNCS, vol. 13847, 518–534.","ieee":"Y. Nemcovsky, M. Jacoby, A. M. Bronstein, and C. Baskin, “Physical passive patch adversarial attacks on visual odometry systems,” in <i>16th Asian Conference on Computer Vision</i>, Macao, China, 2023, vol. 13847, pp. 518–534."},"status":"public","date_published":"2023-03-11T00:00:00Z","month":"03","oa":1,"page":"518-534","conference":{"start_date":"2022-12-04","end_date":"2022-12-08","location":"Macao, China","name":"ACCV: Asian Conference on Computer Vision"},"volume":13847,"publication_identifier":{"eissn":["1611-3349"],"issn":["0302-9743"],"eisbn":["9783031262937"],"isbn":["9783031262920"]},"quality_controlled":"1","date_created":"2024-10-08T12:51:14Z","extern":"1","alternative_title":["LNCS"],"intvolume":"     13847","type":"conference","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2207.05729","open_access":"1"}],"day":"11","publication":"16th Asian Conference on Computer Vision","publisher":"Springer Nature","oa_version":"Preprint","doi":"10.1007/978-3-031-26293-7_31"}