This thesis is a research into developing a methodology and implementation of automated gray-box Broken Access Control Scanning (BACS) in web applications. Broken access controls take first place in the OWASP Top Ten Web Application Security Risks 2021. The need for this research comes from the observation that testing for broken access controls in web applications is labor-intensive, time-consuming, and error-prone. Therefore, security researchers require a modern methodology and toolset for exhaustively discovering access control vulnerabilities in web applications.

The posited hypothesis is that the contextual awareness required for access controls can be achieved by assuming that users are only authorized to perform actions accessible via the UI for that particular user. The methodology developed in this research consists of four phases: 1) A crawl phase where an application is crawled as multiple users. 2) A request selection phase, where potentially vulnerable requests are selected. 3) A request replay phase, where selected requests are replayed in the session context of another user. 4) A response comparison phase to identify whether an access control vulnerability has occurred. An implementation is provided and evaluated during web application penetration tests of DongIT. The results show that critical and structural access control issues can be identified when all four stages are completed. However, the intricacies of web applications often pose challenges for one or more of the four stages. From the results, it is concluded that the BACS methodology is a viable strategy and a valuable tool in the toolbelt of a security tester. ... Read more

Algorithms that recommend items to users are known as recommender systems and have become an important part of online ecosystems. These systems calculate the similarity between given users or items based on the ratings they have received. Such similarities can be modeled as a graph where users or items (nodes) have connections (edges) to other users or items if the ratings they possess are alike. Using a graphical representation allows for the use of graph regularisers. These techniques predict ratings for a given user or item by using the ratings of users or items that are connected to the target in the graph. For the Total Variation Regulariser, much is still unclear concerning its performance when applied to Item KNN Collaborative Filtering. This report will show why Item Total Variation was unable to out-perform more traditional recommender systems in the conducted experiments. The findings indicate how this poor performance could in part be attributed to the choice in dataset. Additional results also convey that Total Variation may be predisposed to performing worse for a certain type of metric. ... Read more

Recommender systems (RS) assist users in making decisions by filtering content that the user would likely find relevant. Standard techniques like collaborative filtering exploit user similarities to find the recommendations assuming that similar users are likely to be interested in the same items. On the other hand, graph RS borrow techniques from the field of graph signal processing to predict ratings for items that the users have not seen and utilize a graph representation of user similarities and their corresponding ratings. Recent studies indicated that simple RS could outperform the state-of-the-art RS. Therefore our paper contributes by analyzing the performance of a novel approach to RS - collaborative filtering that uses a total variation graph regularizer. We show that total variation can outperform its predecessor collaborative filtering by reducing the root mean squared error by 4.68%. However, further experiments with top-n recommendations indicated that traditional collaborative filtering could recommend more relevant content than the total variation, which is supported by a 2.20% increase in precision. The results indicate that total variation alone does not add more information to the RS to show noteworthy improvements to existing traditional baselines. However, building on discoveries that even some of the state-of-the-art RS cannot outperform well-defined baselines, a 4.68% increase in accuracy reveals the potential of RS supported by graph regularization.
... Read more

Collaborative filtering is used to predict the preference or rating of a user for a certain item. Collaborative filtering is based on the notion that similar users rate similarly. A lot of research is done on how to improve this algorithm, mostly with deep learning. A less investigated field for recommender systems is graph signal processing. Graph signal processing is used to reconstruct a graph signal based on the surrounding nodes. The item ratings of a user can be represented as a graph signal. So it is possible to use graph signal processing as a recommender system. In this paper we investigate how the Tikhonov and Sobolev graph regularisers perform for user-based KNN collaborative filtering. We investigated this by comparing the performance of the collaborative filtering algorithm with the two graph regularisers. We found that the Tikhonov regulariser and the Sobolev regulariser performed very similar to user-based KNN collaborative filtering. This means that the added complexity of the graph regularisers did not increase the quality of predictions we can already make with collaborative filtering. ... Read more

A recommendation algorithm aims to predict the quality of a user's future interaction with certain items based on their previous interactions. As research progresses, these algorithms are becoming increasingly more complicated with the use of machine learning and neural networks. This paper looks into a more simple solution. The recommendation domain can be represented as a graph, meaning different graph regularization techniques can be used to solve the same problem. After running experiments comparing the Item-Item Tikhonov Regularizer and the Sobolev Regularizer to a baseline, the item-item standard Collaborative Filtering method, it is clear that the Graph Regularization techniques outperform the baseline. Given that it has been shown that Collaborative Filtering is a relatively competitive method in this field, outperforming it means that Graph Regularizers are a viable and potentially competitive method for solving the recommender problem. ... Read more

The upcoming IEEE 802.1CB standard aims to solve performance and reliability issues in Time-Sensitive Networking (TSN). Mission-critical systems often use these standards for communication in automotive, industrial, and avionic networks. However, researchers did not sufficiently investigate the security risks and possible mitigation solutions to this introduced standard. This limited knowledge is a problem as Cyber-Physical Systems (CPS) are mission-critical and time-sensitive, and any unexpected failure of these systems could endanger lives.

To attain a complete overview of the security risks of IEEE 802.1CB, we use an improved STRIDE model for Cyber-Physical Systems. We then design and create a hardware test-bed for Time-Sensitive Networking to prove the feasibility of the identified security risks. Finally, we implement attacks for the identified security risks in IEEE 802.1CB and analyze their impact by running experiments on the hardware test-bed. The results show that some of the identified security risks significantly impact the network’s reliability as we successfully execute a Replay attack and a Denial of Service attack. However, the hardware switches provide only limited functionality of the IEEE 802.1CB specification. Therefore, we could not verify the attacks against all identified security risks.

These results show that this networking standard is not ready to be used in Cyber-Physical Systems as the impact of the identified security risks is too significant. On this basis, we recommend additional research and improvements to the IEEE 802.1CB standard and mitigation solutions. ... Read more

In the field of ecology, camera traps are important tools to collect information on the wildlife of certain areas. The problem that arises with many camera traps is that they can collect more images than a human can realistically go trough all by themselves. To help classify these images computer vision is proposed as an alternative to manual classification. Many modern computer vision applications use neural networks. A hard part for the neural networks is that to train them well a large data set is needed, and sometimes it is almost impossible to build this dataset. This is where synthetic samples can be used instead of real samples. These samples are created by using computer graphics software to create realistic looking images to enlarge the dataset, or even be the whole dataset. This work evaluates how well a segmentation network was trained on only synthetic samples could perform on the real data. For this multiple segmentation networks were used like: U-Net and SegNet and the networks were trained on different datasets all derived from the synthetic data. The results show that while the networks can work real images that look similar to the synthetic samples, they fail to segment images that are captured in locations that look different from the synthetic samples. ... Read more

We present a technique for enhancing high-dynamic-range tone mapping algorithms by adding the bloom effect to bright areas. Bloom is based on the fact that real-life lenses convolve light and make bright areas emit a glow. The algorithm takes a set of images with different exposures as input, and performs a tone mapping algorithm on these. It then takes the image with the lowest exposure value to create the bloom effect. It then perform a convolution on this image with with a kernel that represents the response to one point of light. The resulting image is then added on top of the tone mapped image. We also present parameters to change the spread of the glowing effect, how bright an area needs to be to get a significant glow, and the intensity of the glow when applied. Furthermore, the kernel can be changed to create different types of glow and highlights. These things make the technique versatile and allows the photographer to customize the effect. ... Read more

In this paper, we investigate the problem of segmenting the foreground objects from the known background. The target application is a setting where a large display serves as the backdrop for a scene. The method proposed in this paper solves this problem in two steps. We try to separate the foreground and the background with the modified background subtraction base technique, which involves taking the per-pixel difference of the image with and without the foreground. The modification includes blurring the image before taking the difference and finding contours to separate noise and small objects in the background from the foreground. If the background subtraction fails, the chroma-key method is used: we put the solid colour screen behind the foreground object to ease the separation. To minimize the adverse effects of the chroma-key on the lighting of the objects, we propose the method for the background screen minimization using the pinhole camera theory. ... Read more

Camera traps are used around the world to provide data on species, population sizes and how species are interacting. However this creates a lot of work in identifying which animal was actually spotted near the camera. Attempts have been made to use deep-learning to identify animals and work correctly for animals which are not rare but the lack of training data of rare species is a hurdle yet to be overcome. This research is focused how well the MIT Data-Efficient Generative Adversarial Network or MITGAN for short can generate realistic samples to be used as training data. For this we use a modified version of the CCT20 data-set. Which has artificially made a single rare class: the deer class. We trained a MITGAN model to generate images of our artificial rare class and used these images to train a classification model. This model was then compared to a baseline model as well as an oversampled model. From this it follows that using the MITGAN model to generate extra samples for our rare class is not worth the effort it takes compared to the precision increase in the rare class.
... Read more

To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples. As a testbed, we use a camera trap animal dataset with a rare deer class, which is augmented with synthetic deer samples. We adapt existing domain adaptation methods to two new methods for the single rare class setting: DeerDANN, based on the Domain-Adversarial Neural Network (DANN), and DeerCORAL, based on deep correlation alignment (Deep CORAL) architectures. Experiments show that DeerDANN has the highest improvement in deer classification accuracy of 24.0% versus 22.4% improvement of DeerCORAL when compared to the baseline. Further, both methods require fewer than 10k synthetic samples, as used by the baseline, to achieve these higher accuracies. DeerCORAL requires the least number of synthetic samples (2k deer), followed by DeerDANN (8k deer). ... Read more

We live in a world where much of our interactions with the environment around us depend on us being physically close to them. For instance, we have proximity­based tokens (e.g., keys and smartcards) for access systems installed at various places such as in cars, at contactless payment terminals, and in electronic passports. Moreover, such systems exist in critical environments like nuclear power plants.Unfortunately, the current systems used to detect proximity between devices and/or users are rife with vulnerabilities. Numerous attacks, such as Relay attack, Preamble Injection attack, Early Detect/Late Commit, and Cicada, exist that let an attacker maliciously alter the measured distance. The research community has proposed several solutions to address these problems and based on their inputs, the IEEE 802.15.4a standard was recently amended. Nevertheless, we show that the newer amendment(i.e., IEEE 802.15.4z) is however not entirely secure and still vulnerable to being exploited.In this work, we evaluate and address the vulnerabilities present in the recently introduced standard,IEEE 802.15.4z amendment for Ultra­Wide Band (UWB). This standard forms the basis of proximity detection in a majority of new devices such as keyfobs for cars, access control systems, smartphones like Samsung S21 and Google Pixel 6, and even medical equipment to monitor patients. First, we mount two attacks, namely the Cicada­TF and the Adaptive Injection, against UWB ­based proximity detection systems. Second, we propose a novel approach to detect the presence of these attacks. We create a real ­world testbed using DWM3000 ICs mounted on NRF52840­devkits to launch the attacks and implement our proposed detection approach. We evaluate the efficacy of our approach in three different environments: an indoor residence, a large outdoor passageway, and an office space. These environments were selected to represent the most commonly used places and were based on the802.15.4a channel models document by IEEE. Our experiment results show that the proposed model can detect the presence of attacks with high accuracy (94%) in all three environments. To the best of our knowledge, this is the first research work that presents a way to detect the presence of such attacks and also to be verified on hardware. ... Read more