Adversarial Video Promotion Against Text-to-video Retrieval

Abstract

Thanks to the development of cross-modal models, text-to-video retrieval (T2VR) is advancing rapidly, but its robustness remains largely unexamined. Existing attacks against T2VR are designed to push videos away from queries, i.e., suppressing the ranks of videos, while the attacks that pull videos towards selected queries, i.e., promoting the ranks of videos, remain largely unexplored. These attacks can be more impactful as attackers may gain more views/clicks for financial benefits and widespread (mis)information. To this end, we pioneer the first attack against T2VR to promote videos adversarially, dubbed the Video Promotion attack (ViPro). We further propose Modal Refinement (MoRe) to capture the finer-grained, intricate interaction between visual and textual modalities to enhance black-box transferability. Comprehensive experiments cover 2 existing baselines, 3 leading T2VR models, 3 prevailing datasets with over 10k videos, evaluated under 3 scenarios. All experiments are conduct

Stats

• citations0
• S2 citations—
• github stars4
• HF likes0
• heat score1.40
• arxiv keytian2025adversarial

Related papers

• PRVR: Partially Relevant Video Retrieval (2022)2.26
• Video-colbert: Contextualized Late Interaction For Text-to-video Retrieval (2025)5.24
• T2vparser: Adaptive Decomposition Tokens For Partial Alignment In Text To Video Retrieval (2025)0.95
• UATVR: Uncertainty-adaptive Text-video Retrieval (2023)15.46
• Are Synthetic Videos Useful? A Benchmark For Retrieval-centric Evaluation Of Synthetic Videos (2025)4.52
• Prota: Probabilistic Token Aggregation For Text-video Retrieval (2024)4.52
• Continual Text-to-video Retrieval With Frame Fusion And Task-aware Routing (2025)8.75
• Mv-adapter: Multimodal Video Transfer Learning For Video Text Retrieval (2023)9.76