Image source forensics is widely considered as one of the most effective ways to verify in a
blind way digital image authenticity and integrity. In the last few years, many researchers …

In transferable black-box attacks, adversarial samples remain adversarial across multiple
models and are more likely to attack unknown models. From this view, acquiring and …

Recent years, the development of DeepFake has raise a lot of security problems. Therefore,
detection of DeepFake is critical. However, the existing DeepFake detection methods are …

Deep neural networks (DNNs) have been shown to be susceptible to critical vulnerabilities
when attacked by adversarial samples. This has prompted the development of attack and …

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks
can fool neural networks with small adversarial perturbations, especially for large size …

Artificial neural networks have become the go-to solution for computer vision tasks, including
problems of the security domain. One such example comes in the form of reidentification …

We study transfer-based adversarial attacks that introduce perturbations in an image that are
large enough to make an unknown CNN wrongly classify it. These perturbations should also …

OpenSim is a modeling and simulation-based open source software for the purpose of
advanced rehabilitation research work. It has an extensive range of applications, which …

Competitions have become an integral part of advancing state-of-the-art in artificial
intelligence (AI). They exhibit one important difference to benchmarks: Competitions test a …

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