Background Artificial intelligence (AI) image generation has opened up endless possibilities for creativity, allowing architects, designers, and artists to produce visual models rapidly. However, this technology is responsible for creating deepfakes, which are highly realistic but fake images and videos. Deepfakes can be used to spread misinformation,...

Machine learning models and neural networks in particular can be used in the field of image processing. Machine learning models are trained to better improve their output quality. During training, domain generalization is the problem of making accurate predictions on previously unseen domains, especially when these domains are very different from...

Conventional methods used for reconstructing road traffic scenes often rely on fixed sensors and cameras entrenched within road infrastructure. However, these approaches grapple with substantial limitations in terms of scope, cost-efficiency, and safeguarding individual privacy. The need to fortify road safety, strengthen urban planning initiatives,...

In the rapidly advancing landscape of deep reinforcement learning (RL), recent studies have highlighted vulnerabilities in control policies learned through deep RL. These vulnerabilities raise concerns surrounding adversarial attacks, especially in risk-sensitive domains such as autonomous driving. In these scenarios, the learned policies become susceptible...

­Background Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated from. Existing studies showed empirical feasibility of attribution...

Clinical assessment of upper extremity function typically relies on subjective evaluation of movement quality and/or time spent to complete a given task. This is neither objective nor sensitive enough for subtle changes related to patient progression. Some systems use motion analysis with skeletal tracking software. However, these systems do not perform...