Text-to-image diffusion models are nothing but a revolution, allowing anyone, even without
design skills, to create realistic images from simple text inputs. With powerful personalization …

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its
privacy implications intensifies. Despite a growing corpus of research in AI privacy and …

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an
encoder which can be used as a general-purpose feature extractor, such that downstream …

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as
CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit …

Facial expression recognition (FER) is embedded in many real-world human-computer
interaction tasks, such as online learning, depression recognition and remote diagnosis …

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a
predominant solution within the deep learning landscape. Model providers furnish pre …

The success of deep learning based face recognition systems has given rise to serious
privacy concerns due to their ability to enable unauthorized tracking of users in the digital …

The success of deep face recognition (FR) systems has raised serious privacy concerns due
to their ability to enable unauthorized tracking of users in the digital world. Previous studies …

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible
perturbations to benign examples. The attack transferability enables adversarial examples to …

Traditional personal image privacy protection usually suffers from the overprotection
problem, where one or more undesired persons in an image may be inevitably shielded …