{"type":"ScholarlyArticle","title":"Transferable Attacks on Open-Vocabulary Video Instance Segmentation via Dual-Objective Triggers","authors":[{"name":"Minghao Shou","slug":"minghao-shou","given":"Minghao","family":"Shou","affiliation":""},{"name":"Kesen Wang","slug":"kesen-wang","given":"Kesen","family":"Wang","affiliation":""},{"name":"Tong Zhang","slug":"tong-zhang","given":"Tong","family":"Zhang","affiliation":""},{"name":"Han Bao","slug":"han-bao","given":"Han","family":"Bao","affiliation":""},{"name":"Zonghui Wang","slug":"zonghui-wang","given":"Zonghui","family":"Wang","affiliation":""}],"abstract":"Open‑vocabulary video instance segmentation (OV‑VIS) couples spatial‑temporal reasoning with language grounding, yet its adversarial robustness has remained unexplored. We present the Dual-Objective Triggers (DOT), the first transferable attack on OV-VIS that simultaneously exploits the vision–language coupling and temporal coherence. DOT deploys a Dual Semantic Perturbation Module that overlays two complementary triggers: a Semantic Suppression Trigger erases the alignment between the true object and the query, while a Plausible Replacement Trigger steers the tracker toward a phantom trajectory that is visually plausible and text‑consistent. To amplify cross‑model transferability without sacrificing perceptual fidelity, we introduce Phase‑Guided Adversarial Training, which injects perturbations primarily in the phase spectrum while blending amplitudes with clean references. Extensive experiments on four state‑of‑the‑art OV‑VIS implementations demonstrate that DOT reduces mAP by up to 69.3% and raises attack success rate by up to 98%, outperforming the strongest baselines by a factor of 1.6× on average, while maintaining a PSNR of 52.49 dB, thus exposing critical security vulnerabilities and laying a foundation for future research on robust and trustworthy vision–language systems.","doi":"10.24963/ijcai.2026/180","url":"https://ijcai.org/proceedings/2026/180","pdf":"https://ijcai.org/proceedings/2026/0180.pdf","markdown":"https://ijcai.org/proceedings/2026/180.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/180","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":180,"pages":{"first":1613,"last":1621},"keywords":["Computer Vision: Adversarial learning, adversarial attack and defense methods","Machine Learning: Multi-modal learning","Computer Vision: Video analysis and understanding","Machine Learning: Adversarial machine learning","Computer Vision: Vision, language and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}