{"ID":2852094,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18362","arxiv_id":"2510.18362","title":"FeatureFool: Zero-Query Fooling of Video Models via Feature Map","abstract":"The vulnerability of deep neural networks (DNNs) has been preliminarily verified. Existing black-box adversarial attacks usually require multi-round interaction with the model and consume numerous queries, which is impractical in the real-world and hard to scale to recently emerged Video-LLMs. Moreover, no attack in the video domain directly leverages feature maps to shift the clean-video feature space. We therefore propose FeatureFool, a stealthy, video-domain, zero-query black-box attack that utilizes information extracted from a DNN to alter the feature space of clean videos. Unlike query-based methods that rely on iterative interaction, FeatureFool performs a zero-query attack by directly exploiting DNN-extracted information. This efficient approach is unprecedented in the video domain. Experiments show that FeatureFool achieves an attack success rate above 70\\% against traditional video classifiers without any queries. Benefiting from the transferability of the feature map, it can also craft harmful content and bypass Video-LLM recognition. Additionally, adversarial videos generated by FeatureFool exhibit high quality in terms of SSIM, PSNR, and Temporal-Inconsistency, making the attack barely perceptible. This paper may contain violent or explicit content.","short_abstract":"The vulnerability of deep neural networks (DNNs) has been preliminarily verified. Existing black-box adversarial attacks usually require multi-round interaction with the model and consume numerous queries, which is impractical in the real-world and hard to scale to recently emerged Video-LLMs. Moreover, no attack in th...","url_abs":"https://arxiv.org/abs/2510.18362","url_pdf":"https://arxiv.org/pdf/2510.18362v2","authors":"[\"Duoxun Tang\",\"Xi Xiao\",\"Guangwu Hu\",\"Kangkang Sun\",\"Xiao Yang\",\"Dongyang Chen\",\"Qing Li\",\"Yongjie Yin\",\"Jiyao Wang\"]","published":"2025-10-21T07:33:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\"]","has_code":false}