Adversarial attacks can evaluate model robustness and have been of great concerns in
recent years. Among various attacks, targeted attacks aim at misleading victim models to …

The strategy of ensemble has become popular in adversarial defense, which trains multiple
base classifiers to defend against adversarial attacks in a cooperative manner. Despite the …

Transferable targeted adversarial attacks aim to mislead models into outputting adversary-
specified predictions in black-box scenarios. Recent studies have introduced single-target …

The emergence of face forgery has raised global concerns on social security, thereby
facilitating the research on automatic forgery detection. Although current forgery detectors …

In transferable black-box attacks, adversarial samples remain adversarial across multiple
models and are more likely to attack unknown models. From this view, acquiring and …

Adversarial examples have shown a powerful ability to make a well-trained model
misclassified. Current mainstream adversarial attack methods only consider one of the …

In the black-box attack for speaker recognition systems, the adversarial examples can
exhibit better transferability for unseen victim system if they can consistently spoof an …

DIFFERENTIAL GEOMETRY INSPIRED MACHINE LEARNING SOLUTIONS Page 1
DIFFERENTIAL GEOMETRY INSPIRED MACHINE LEARNING SOLUTIONS Athesis …