Ahmet Kondoz

By design, distributed ledger technologies persist low-level data, which makes conducting complex business analysis of the recorded operations challenging. Existing blockchain visualization and analytics tools such as block explorers tend to rely on this low-level data and complex interfacing to provide an enriched level of analytics. The ability to derive richer analytics could be improved through the availability of a higher level abstraction of the data. This article proposes an abstraction layer architecture that enables the design of high-level analytics of distributed ledger systems and the decentralized applications that run on top. Based on the analysis of existing initiatives and identification of the relevant user requirements, this work aims to establish key insights and specifications to improve the auditability and intuitiveness of distributed ledger systems by leveraging the development of future user interfaces. To illustrate the benefits offered by the proposed abstraction layer architecture, a regulated sector use case is explored.

Despite the widespread use of encryption techniques to provide confidentiality over Internet communications, mobile device users are still susceptible to privacy and security risks. In this paper, a novel Deep Neural Network (DNN) based on a user activity detection framework is proposed to identify fine-grained user activities performed on mobile applications (known as in-app activities) from a sniffed encrypted Internet traffic stream. One of the challenges is that there are countless applications, and it is practically impossible to collect and train a DNN model using all possible data from them. Therefore, in this work, we exploit the probability distribution of a DNN output layer to filter the data from applications that are not considered during the model training (i.e., unknown data). The proposed framework uses a time window-based approach to divide the traffic flow of activity into segments so that in-app activities can be identified just by observing only a fraction of the activity-related traffic. Our tests have shown that the DNN-based framework has demonstrated an accuracy of 90% or above in identifying previously trained in-app activities and an average accuracy of 79% in identifying previously untrained in-app activity traffic as unknown data when this framework is employed.

In this study, a simple yet effective framework is proposed to characterize fine-grained in-app user activities performed on mobile applications using a convolutional neural network (CNN). The proposed framework uses a time window-based approach to split the activity’s encrypted traffic flow into segments, so that in-app activities can be identified just by observing only a part of the activity-related encrypted traffic. In this study, matrices were constructed for each encrypted traffic flow segment. These matrices acted as input into the CNN model, allowing it to learn to differentiate previously trained (known) and previously untrained (unknown) in-app activities as well as the known in-app activity type. The proposed method extracts and selects salient features for encrypted traffic classification. This is the first-known approach proposing to filter unknown traffic with an average accuracy of 88%. Once the unknown traffic is filtered, the classification accuracy of our model would be 92%.

Deep learning, in general, was built on input data transformation and presentation, model training with parameter tuning, and recognition of new observations using the trained model. However, this came with a high computation cost due to the extensive input database and the length of time required in training. Despite the model learning its parameters from the transformed input data, no direct research has been conducted to investigate the mathematical relationship between the transformed information (i.e., features, excitation) and the model’s learnt parameters (i.e., weights). This research aims to explore a mathematical relationship between the input excitations and the weights of a trained convolutional neural network. The objective is to investigate three aspects of this assumed feature-weight relationship: (1) the mathematical relationship between the training input images’ features and the model’s learnt parameters, (2) the mathematical relationship between the images’ features of a separate test dataset and a trained model’s learnt parameters, and (3) the mathematical relationship between the difference of training and testing images’ features and the model’s learnt parameters with a separate test dataset. The paper empirically demonstrated the existence of this mathematical relationship between the test image features and the model’s learnt weights by the ANOVA analysis.

Deep learning has proven to be an important element of modern data processing technology, which has found its application in many areas such as multimodal sensor data processing and understanding, data generation and anomaly detection. While the use of deep learning is booming in many real-world tasks, the internal processes of how it draws results is still uncertain. Understanding the data processing pathways within a deep neural network is important for transparency and better resource utilisation. In this paper, a method utilising information theoretic measures is used to reveal the typical learning patterns of convolutional neural networks, which are commonly used for image processing tasks. For this purpose, training samples, true labels and estimated labels are considered to be random variables. The mutual information and conditional entropy between these variables are then studied using information theoretical measures. This paper shows that more convolutional layers in the network improve its learning and unnecessarily higher numbers of convolutional layers do not improve the learning any further. The number of convolutional layers that need to be added to a neural network to gain the desired learning level can be determined with the help of theoretic information quantities including entropy, inequality and mutual information among the inputs to the network. The kernel size of convolutional layers only affects the learning speed of the network. This study also shows that where the dropout layer is applied to has no significant effects on the learning of networks with a lower dropout rate, and it is better placed immediately after the last convolutional layer with higher dropout rates.

Reinforcement learning (RL) is a booming area in artificial intelligence. The applications of RL are endless nowadays, ranging from fields such as medicine or finance to manufacturing or the gaming industry. Although multiple works argue that RL can be key to a great part of intelligent vehicle control related problems, there are many practical problems that need to be addressed, such as safety related problems that can result from non-optimal training in RL. For instance, for an RL agent to be effective it should first cover all the situations during training that it may face later. This is often difficult when applied to the real-world. In this work we investigate the impact of RL applied to the context of intelligent vehicle control. We analyse the implications of RL in path planning tasks and we discuss two possible approaches to overcome the gap between the theorical developments of RL and its practical applications. Specifically, firstly this paper discusses the role of Curriculum Learning (CL) to structure the learning process of intelligent vehicle control in a gradual way. The results show how CL can play an important role in training agents in such context. Secondly, we discuss a method of transferring RL policies from simulation to reality in order to make the agent experience situations in simulation, so it knows how to react to them in reality. For that, we use Arduino Yún controlled robots as our platforms. The results enhance the effectiveness of the presented approach and show how RL policies can be transferred from simulation to reality even when the platforms are resource limited.

Creating an accurate awareness of the environment using laser scanners is a major challenge in robotics and auto industries. LiDAR (light detection and ranging) is a powerful laser scanner that provides a detailed map of the environment. However, efficient and accurate mapping of the environment is yet to be obtained, as most modern environments contain glass, which is invisible to LiDAR. In this paper, a method to effectively detect and localise glass using LiDAR sensors is proposed. This new approach is based on the variation of range measurements between neighbouring point clouds, using a two-step filter. The first filter examines the change in the standard deviation of neighbouring clouds. The second filter uses a change in distance and intensity between neighbouring pules to refine the results from the first filter and estimate the glass profile width before updating the cartesian coordinate and range measurement by the instrument. Test results demonstrate the detection and localisation of glass and the elimination of errors caused by glass in occupancy grid maps. This novel method detects frameless glass from a long range and does not depend on intensity peak with an accuracy of 96.2%.

Privacy-preserving applications allow users to perform on-line daily actions without leaking sensitive information. The privacy-preserving scalar product is one of the critical algorithms in many private applications. The state-of-the-art privacy-preserving scalar product schemes use either computationally intensive homomorphic (public-key) encryption techniques such as Paillier encryption to achieve strong security (i.e., 128-bit) or random masking technique to achieve high efficiency for low security. In this paper, lattice structures have been exploited to develop an efficient privacy-preserving system. The proposed scheme is not only efficient in computation as compared to the state-of-the-art but also provides high degree of security against quantum attacks. Rigorous security and privacy analyses of the proposed scheme have been provided along with a concrete set of parameters to achieve 128-bit and 256-bit security. Performance analysis shows that the scheme is at least five orders faster than the Paillier schemes and at least twice as faster than the existing randomisation technique at 128-bit security. Also the proposed scheme requires six-time fewer data compared to Paillier and randomisation based schemes for communications.