Recently, intrusion detection methods based on supervised deep learning techniques (DL) have seen widespread adoption by the research community, as a result of advantages, such as the ability to learn useful feature representations from input data without excessive manual intervention. However, these techniques require large amounts of data to generalize well. Collecting a large-scale malicious sample is non-trivial, especially in the modern day with its constantly evolving landscape of cyber-threats. On the other hand, collecting a few-shot of malicious samples is more realistic in practical settings, as in cases such as zero-day attacks, where security agents are only able to intercept a limited number of such samples. Hence, intrusion detection methods based on few-shot learning is emerging as an alternative to conventional supervised learning approaches to simulate more realistic settings. Therefore, in this paper, we propose a novel method that leverages discriminative representation learning with a supervised autoencoder to achieve few-shot intrusion detection. Our approach is implemented in two stages: we first train a feature extractor model with known classes of malicious samples using a discriminative autoencoder, and then in the few-shot detection stage, we use the trained feature extractor model to fit a classifier with a few-shot examples of the novel attack class. We are able to achieve detection rates of 99.5% and 99.8% for both the CIC-IDS2017 and NSL-KDD datasets, respectively, using only 10 examples of an unseen attack.
Understanding the ways different people perceive and apply acquired knowledge, especially when driving, is an important area of study. This study introduced a novel virtual reality (VR)-based driving system to determine the effects of neuro-cognitive load on learning transfer. In the experiment, easy and difficult routes were introduced to the participants, and the VR system is capable of recording eye-gaze, pupil dilation, heart rate, as well as driving performance data. So, the main purpose here is to apply multimodal data fusion, several machine learning algorithms, and strategic analytic methods to measure neurocognitive load for user classification. A total of ninety-eight (98) university students participated in the experiment, in which forty-nine (49) were male participants and forty-nine (49) were female participants. The results showed that data fusion methods achieved higher accuracy compared to other classification methods. These findings highlight the importance of physiological monitoring to measure mental workload during the process of learning transfer.
Investigating whether landmarks and routes affect navigational efficiency and learning transfer in traffic is essential. In this study, a virtual reality-based driving system was employed to determine the effects of landmarks and routes on human neurocognitive behavior. The participants made four (4) journeys to predetermined destinations. They were provided with different landmarks and routes to aid in reaching their respective destinations. We considered two (2) groups and conducted two (2) sessions per group in this study. Each group had sufficient and insufficient landmarks. We hypothesized that using insufficient landmarks would elicit an increase in psychophysiological activation, such as increased heart rate, eye gaze, and pupil size, which would cause participants to make more errors. Moreover, easy and difficult routes elicited different cognitive workloads. Thus, a high cognitive load would negatively affect the participants when trying to apply the knowledge acquired at the beginning of the exercise. In addition, the navigational efficiency of routes with sufficient landmarks was remarkably higher than that of routes with insufficient landmarks. We evaluated the effects of landmarks and routes by assessing the recorded information of the drivers’ pupil size, heart rate, and driving performance data. An analytical strategy, several machine learning algorithms, and data fusion methods have been employed to measure the neurocognitive load of each participant for user classification. The results showed that insufficient landmarks and difficult routes increased pupil size and heart rate, which caused the participants to make more errors. The results also indicated that easy routes with sufficient landmarks were deemed more efficient for navigation, where users’ cognitive loads were much lower than those with insufficient landmarks and difficult routes. The high cognitive workload hindered the participants when trying to apply the knowledge acquired at the beginning of the exercise. Meanwhile, the data fusion method achieved higher accuracy than the other classification methods. The results of this study will help improve the use of landmarks and design of driving routes, as well as paving the way to analyze traffic safety using the drivers’ cognition and performance data.