{"data":{"id":"5179a73c-c5a5-46d3-b8a1-48ec9a52b263","title":"Transferable Adversarial Attack on Referring Video Object Segmentation","summary":"This work presents the first comprehensive study of adversarial robustness in referring video object segmentation (RVOS) models, which segment text-referred objects in video and matter for safety-critical uses such as autonomous driving. The authors propose xM-ICM, a cross-prompt multimodal attack that jointly corrupts visual and textual embeddings and uses two momentum banks to keep perturbations coherent across clips. Experiments on three benchmarks and five RVOS models report strong white-box attack performance and good black-box transferability.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11480168","publishedAt":"2026-04-13T13:17:15.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-04-13T13:17:15.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":null}}