An Attempt of Evolutionary Generation of Adversarial Examples for One-Shot Depth Estimation

DOI

Bibliographic Information

Other Title
  • 単眼深度推定器に対する敵対的事例の進化的生成の試み

Description

<p>With recent advances of Deep Neural Networks(DNNs), the performance of monocular depth estimationhas been improved and expectations for its practical use are increasing. On the other hand, recent studies haverevealed vulnerabilities of DNNs, in which carefully designed perturbations called adversarial examples can causemisclassi cation. It is essential to investigate such vulnerabilities so that DNN-based one-shot depth estimatorscan be safely applied to real-world applications. Therefore, this study proposes an evolutionary computation-based method to generate adversarial examples that cause one-shot depth estimators to measures make incorrectmeasurements. The proposed method performs targeted attack under black-box condition by adding perturbationson a target object so that a target object would not be detected. Experimental results demonstrated that theproposed method successfully generated AEs that misleaded a well-known DNN-based one-shot depth estimator.</p>

Journal

Keywords

Details 詳細情報について

  • CRID
    1390285300166397312
  • NII Article ID
    130007857387
  • DOI
    10.11517/pjsai.jsai2020.0_4j3gs203
  • ISSN
    27587347
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top