Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
European Conference on Computer Vision(2020)
摘要
Deep neural networks are known to be susceptible to adversarial noise, which is tiny and imperceptible perturbation. Most of previous works on adversarial attack mainly focus on image models, while the vulnerability of video models is less explored. In this paper, we aim to attack video models by utilizing intrinsic movement pattern and regional relative motion among video frames. We propose an effective motion-excited sampler to obtain motion-aware noise prior, which we term as sparked prior. Our sparked prior underlines frame correlations and utilizes video dynamics via relative motion. By using the sparked prior in gradient estimation, we can successfully attack a variety of video classification models with fewer number of queries. Extensive experimental results on four benchmark datasets validate the efficacy of our proposed method.
更多查看译文
关键词
Video adversarial attack,Video motion,Noise sampler
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络