Search-and-Attack: Temporally Sparse Adversarial Perturbations on Videos

Hwan Heo, Dohwan Ko, Jaewon Lee, Youngjoon Hong, Hyunwoo J. Kim

Research output: Contribution to journalArticlepeer-review

Abstract

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 Search-and-Attack scheme, on videos. The Search-and-Attack 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.

Original languageEnglish
Pages (from-to)146938-146947
Number of pages10
JournalIEEE Access
Volume9
DOIs
Publication statusPublished - 2021

Keywords

  • Action recognition
  • adversarial attack
  • safe AI
  • sparse adversarial attack
  • video classification

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint

Dive into the research topics of 'Search-and-Attack: Temporally Sparse Adversarial Perturbations on Videos'. Together they form a unique fingerprint.

Cite this