No abstract

Deepfake represents a category of face-swapping attacks that leverage machine learning models such as autoencoders or generative adversarial networks. Although the concept of the face-swapping is not new, its recent technical advances make fake content (e.g., images, videos) more realistic and imperceptible to Humans. Various detection techniques for Deepfake attacks have been explored. These methods, however, are passive measures against Deepfakes as they are mitigation strategies after the high-quality fake content is generated. More importantly, we would like to think ahead of the attackers with robust defenses. This work aims to take an offensive measure to impede the generation of high-quality fake images or videos. Specifically, we propose to use novel transformation-aware adversarially perturbed faces as a defense against GAN-based Deepfake attacks. Different from the naïve adversarial faces, our proposed approach leverages differentiable random image transformations during the generation. We also propose to use an ensemblebased approach to enhance the defense robustness against GAN-based Deepfake variants under the black-box setting. We show that training a Deepfake model with adversarial faces can lead to a significant degradation in the quality of synthesized faces. This degradation is twofold. On the one hand, the quality of the synthesized faces is reduced with more visual artifacts such that the synthesized faces are more obviously fake or less convincing to human observers. On the other hand, the synthesized faces can easily be detected based on various metrics.

No abstract

Edge computing network and quantum network are two emerging technologies in current communication fields. Edge computing has emerged to support the computational demand of delay-sensitive applications in which substantial computing and storage are deployed at the network edge close to data sources. Quantum network supports distributed quantum computing, which could provide exponentially computation capabilities for certain problems. The vision of a hybrid quantum-edge is to provide a fundamentally new computing paradigm by expanding the computing capabilities and security of edge computing with quantum computing and quantum communications. The distributed nature of edge computing networks will also enable new scalable quantum networking schemes and applications. Such a hybrid computing paradigm will achieve unparalleled capabilities that are provably impossible by using only classical computing or quantum computing schemes alone. In this paper, we introduce the concept of hybrid quantum-edge computing network and discuss its challenges and opportunities.

No abstract