Mining Attack Strategy: Using Process Mining to extract attacker strategy from IDS alerts

Ever since the invention of the Internet, more and more computers are connected throughout the world. Though this has brought numerous new inventions used every day, like social media, e-commerce, and video conferencing, it also opens up new opportunities for cyber criminals. As the intrusion detection systems used to identify malicious behavior...

The Relation Between Words and Definitions in Combined Word-Sentence Space

Methods for learning vector space representations of words have yielded spaces which contain semantic and syntactic regularities. These regularities mean that vector arithmetic operations in the latent space represent meaningful and interpretable relations between words. These word vectors have been so successful in capturing such relations, as...

Regularization Effect of Dropout

Dropout is one of the most popular regularization methods used in deep learning. The general form of dropout is to add random noise to the training process, limiting the complexity of the models and preventing overfitting. Evidence has shown that dropout can effectively reduce overfitting. This thesis project will show some results where dropout...

Predicting DNA repair-deficient genotypes based on Cas9-induced DNA repair products

Double strand breaks are lesions to the DNA and can be fatal for cells. Therefore these breaks are repaired, primarily by one of the three major repair pathways. Two of these pathways are non-homologous end-joining (NHEJ) and theta-mediated end-joining (TMEJ). These pathways leave genetic alterations in their repair products, a form of DNA...

Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions

Occlusion degrades the performance of human pose estimation. In this paper, we introduce targeted keypoint and body part occlusion attacks. The effects of the attacks are systematically analyzed on the best-performing methods. In addition, we propose occlusion specific data augmentation techniques against keypoint and part attacks. Our extensive...

Machine Learning of Synthetic Lethality: Data Integration, Generalisation, and Selection Bias

Synthetic lethality (SL) arises between two genes when loss of function of both genes would lead cells to become inviable. This can be exploited for therapy, where a drug is used to selectively kill diseased cells by perturbing one gene of an SL pair where the other gene is inactive (e.g. through naturally occurring mutation). Computational...

One-Class Classification: for high-dimensional data

This M.Sc. thesis report investigates the application of one-class classification techniques to complex high-dimensional data. The aim of a one-class classifier is to separate target data from non-target data, but only a dataset containing target data is available for training. The issue with high-dimensional data is that it is difficult to...

Addressing Illumination-Based Domain Shifts in Deep Learning: A Physics-Based Approach

This work investigates how prior knowledge from physics-based reflection models can be used to improve the performance of semantic segmentation models under an illumination-based domain shift. We implement various color invariants as a preprocessing step and find that CNNs trained on these color invariants get stuck in worse local minima...

Automatic Running Event Visualization using Video from Multiple Camera

Visualizing runners trajectory from video data is not straightforward because the video data does not contain the explicit information of which runners appear in the video. Only the visual information related to the runner, such as runner’s unique ID (called bib number), is available. To this end, we propose two automatic runner detection...

Rotation invariant filters in CNNs: applied to segmentation of aerial images for land-use classification

Convolutional neural networks are showing incredible performance in image classification, segmentation, object detection and other computer vision applications in recent years. But they lack understanding of affine transformations to input data. In this work, we introduce rotational invariant<br/>convolutional neural networks that learn...

Example and Feature importance-based Explanations for Black-box Machine Learning Models

Machine Learning (ML) is a rapidly growing field. There has been a surge of complex black-box models with high performance. On the other hand, the application of these models especially in high-risk domains is more stagnant due to lack of transparency and trust in these black-box models. There is a disconnect between the black-box character of...

People Detection from Overhead Cameras: A study of impact of occlusion on performance

During the last decades, people detection has received great attention in computer vision and pattern recognition because of its various applications. Though there are thousands of papers provide approaches for people detection, most of them focus on datasets from side view. People detection from overhead cameras, as an important situation for...

Unsupervised Cross Domain Image Matching with Outlier Detection

This work proposes a method for matching images from different domains in an unsupervised manner, and detecting outlier samples in the target domain at the same time. This matching problem is made difficult by i) the different domain images that are related but under different conditions (e.g. photos of the same location captured in different...