| Summary: | Modern neural networks are known to be vulnerable to adversarial attacks in various domains. Although most attack methods usually densely change the input values, recent works have shown that deep neural networks (DNNs) are also vulnerable to sparse perturbations. Spatially sparse attacks on images or frames of a video are proven effective but the temporally sparse perturbations on videos have been less explored. In this paper, we present a novel framework to generate a temporally sparse adversarial attack, called <italic>Search-and-Attack</italic> scheme, on videos. The <italic>Search-and-Attack</italic> scheme first retrieves the most vulnerable frames and then attacks only those frames. Since identifying the most vulnerable set of frames involves an expensive combinatorial optimization problem, we introduce alternative definitions or surrogate objective functions: Magnitude of the Gradients (MoG) and Frame-wise Robustness Intensity (FRI). Combining them with iterative search schemes, extensive experiments on three public benchmark datasets (UCF, HMDB, and Kinetics) show that the proposed method achieves comparable performance to state-of-the-art dense attack methods.
|
|---|