Deep neural networks (DNNs) have shown remarkable performance improvements on
vision-related tasks such as object detection or image segmentation. Despite their success …

Object tracking belongs to active research areas in computer vision. We are interested in
matching-based trackers exploiting deep machine learning known as Siamese trackers …

Recent studies show that small perturbations in video frames could misguide single object
trackers. However, such attacks have been mainly designed for digital-domain videos (ie …

Although Deep Neural Networks (DNNs) have been widely applied in various real-world
scenarios, they are vulnerable to adversarial examples. The current adversarial attacks in …

The increasing reliance on deep neural network-based object detection models in various
applications has raised significant security concerns due to their vulnerability to adversarial …

Mit der fortschreitenden Integration Künstlicher Intelligenz (KI) in immer mehr Bereiche der
industriellen Prozesse sowie des täglichen Lebens der Menschen steigt die Notwendigkeit …

Advances in deep neural networks have opened a new era of robotics, intelligent robots.
Compared with traditional robots that perform repetitive tasks based on manual control or …

Data-driven deep learning tasks for security related applications are gaining increasing
popularity and achieving impressive performances. This thesis investigates adversarial …