Watch, Listen, Understand, Mislead: Tri-Modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation

Sahid Hossain Mustakim, S. M. Jishanul Islam, Ummay Maria Muna, Montasir Chowdhury, Mohammed Jawwadul Islam, Sadia Ahmmed, Tashfia Sikder, Syed Tasdid Azam Dhrubo, Swakkhar Shatabda. Watch, Listen, Understand, Mislead: Tri-Modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation. In IEEE/CVF International Conference on Computer Vision, ICCV 2025 - Workshops, Honolulu, HI, USA, October 19-20, 2025. pages 2976-2985, IEEE, 2025. [doi]

Abstract

Abstract is missing.