Search Results for author:
Found 4 papers, 1 papers with code
Continual Adversarial Defense
In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible.
Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration
To address this issue, we propose a novel adversarial attack technique known as Adversarial Restoration (AdvRestore), which enhances both visual quality and transferability of adversarial face examples by leveraging a face restoration prior.
Detecting Adversarial Faces Using Only Real Face Self-Perturbations
Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when applied to facial recognition systems.
Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation
Though generating hard samples has shown its effectiveness in improving the generalization of models in training tasks, the effectiveness of utilizing this idea to improve the transferability of adversarial face examples remains unexplored.
