Deepfake has taken the world by storm, triggering a trust crisis. Curren...
The malicious use and widespread dissemination of deepfake pose a signif...
Backdoor attacks pose serious security threats to deep neural networks
(...
Modeling non-Lambertian effects such as facial specularity leads to a mo...
By supervising camera rays between a scene and multi-view image planes, ...
Morphable models are essential for the statistical modeling of 3D faces....
Adversarial training has been widely explored for mitigating attacks aga...
In portraits, eyeglasses may occlude facial regions and generate cast sh...
Prioritizing fairness is of central importance in artificial intelligenc...
Transferability of adversarial examples is of central importance for
att...
Neural networks provide better prediction performance than previous
tech...
(Very early draft)Traditional supervised learning keeps pushing convolut...
Searchable symmetric encryption (SSE) allows the data owner to outsource...
Person re-identification (re-ID) is the task of matching person images a...
Federated learning, i.e., a mobile edge computing framework for deep
lea...