An abstract is not available for this content. As you have access to content, full HTML content provided on page. A PDF of also in through the ‘Save PDF’ action button.

This paper focuses on high-transferable adversarial attacks detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue high transferability, one plausible way is find common property facilitates discovery weaknesses. We first suggest that relevance map from interpreters for detectors such property...