A5035093748- Network Security and Intrusion Detection
- Visual Attention and Saliency Detection
- Media Influence and Health
- Action Observation and Synchronization
- Virtual Reality Applications and Impacts
- Anomaly Detection Techniques and Applications
- Visual perception and processing mechanisms
- Complex Network Analysis Techniques
- Internet Traffic Analysis and Secure E-voting
- Neural Networks and Applications
- Face Recognition and Perception
- Obstructive Sleep Apnea Research
- EEG and Brain-Computer Interfaces
- Explainable Artificial Intelligence (XAI)
- Smart Grid Security and Resilience
Norwegian University of Science and Technology
2023-2024
Osnabrück University
2023-2024
Virtual reality (VR) has become a popular tool for investigating human behavior and brain functions. Nevertheless, it is unclear whether VR constitutes an actual form of or more like advanced simulation. Determining the nature been mostly achieved by self-reported presence measurements, defined as feeling being submerged in experience. However, subjective measurements might be prone to bias and, most importantly, do not allow comparison with real-life experiences. Here, we show that height...
Abstract Conventionally, event-related potential (ERP) analysis relies on the researcher to identify sensors and time points where an effect is expected. However, this approach prone bias may limit ability detect unexpected effects or investigate full range of electroencephalography (EEG) signal. Data-driven approaches circumvent limitation, however, multiple comparison problem statistical correction thereof affect both sensitivity specificity analysis. In study, we present SHERPA – a novel...
The perception of faces is one the most specialized visual processes in human brain and has been investigated by means early event-related potential component N170. However, face mostly studied conventional laboratory, i.e., monitor setups, offering rather distal presentation as planar 2D-images. Increasing spatial proximity through Virtual Reality (VR) allows to present 3D, real-life-sized persons at personal distance participants, thus creating a feeling social involvement adding...
In this paper, we target the problem of mining descriptive profiles computer network intrusion attacks. We present an exploratory and explanation-aware approach using subgroup discovery – facilitating human-in-the-loop interaction for guiding exploration process since results are inherently interpretable patterns. Furthermore, explore enriching feature set describing traffic (i. e., exchanged packets) with a new type features computed on complex networks depicting interactions among...
Nowadays, anomaly-based network intrusion detection system (NIDS) still have limited real-world applications; this is particularly due to false alarms, a lack of datasets, and confidence. In paper, we propose use explainable artificial intelligence (XAI) methods for tackling these issues. our experimentation, train random forest (RF) model on the NSL-KDD dataset, SHAP generate global explanations. We find that explanations deviate substantially from domain expertise. To shed light potential...