Yong-Jie Yin — accepted AI-conference papers

2026

FeatureFool: Zero-Query Fooling of Video Models via Feature Map

Duoxun Tang, Xi Xiao, Guangwu Hu, Kangkang Sun, Xiao Yang, Dongyang Chen +3

CVPR 2026

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. Moreo

Cited by 0 Source ↗Scholar ↗

2026

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach

Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo, Xi Xiao, Yong-Jie Yin +2

AAAI 2026technical

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models—a common and practical real-world scenario—remains unexplored. In this paper, we pioneer an in

Cited by 0 Source ↗PDF ↗Scholar ↗