With technological advances, the generation of deepfake material is now within reach of
those operating consumer-grade hardware. As a result, much research has been …

The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly
prevalent and seeing growing adoption as commercial services, characterizing the social …

Computer vision models have known performance disparities across attributes such as
gender and skin tone. This means during tasks such as classification and detection, model …

Discriminative self-supervised learning allows training models on any random group of
internet images, and possibly recover salient information that helps differentiate between the …

Computer Vision (CV) has achieved remarkable results, outperforming humans in several
tasks. Nonetheless, it may result in significant discrimination if not handled properly. Indeed …

Although effective deepfake detection models have been developed in recent years recent
studies have revealed that these models can result in unfair performance disparities among …

From holistic low-dimension feature-based segmentation to deep polynomial neural
networks, Face Recognition (FR) accuracy has increased dramatically since its early days …

Deep image classifiers have been found to learn biases from datasets. To mitigate the
biases, most previous methods require labels of protected attributes (eg, age, skin tone) as …

Disaggregated evaluations of AI systems, in which system performance is assessed and
reported separately for different groups of people, are conceptually simple. However, their …