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...

It has been pointed out by Katsuno and Mendelzon that the so-called AGM revision operators, defined Alchourrón, Gärdenfors Makinson, do not behave well in dynamically-changing applications. On premise, formally characterized a different type of belief-change typically referred to as KM update which, this date, constitute benchmark belief update. In article, we show there exist operators yield s...