Despite the excellent performance, deep neural networks (DNNs) have been shown to be
vulnerable to adversarial examples. Besides, these examples are often transferable among …

Recognition systems in the remote sensing domain often operate in “open-world”
environments, where they must be capable of accurately classifying data from the in …

Numerous works study black-box attacks on image classifiers, where adversaries generate
adversarial examples against unknown target models without having access to their internal …

Recent research has confirmed the possibility of adversarial attacks on deep models.
However, these methods typically assume that the surrogate model has access to the target …

Existing transfer attack methods commonly assume that the attacker knows the training set
(eg, the label set, the input size) of the black-box victim models, which is usually unrealistic …