Handling the data imbalance problem is one of the crucial steps in a machine learning pipeline. The research community is well aware of the effects of data imbalance on machine learning algorithms. At the same time, there is a rising need for explainability of AI, especially in difficult, high-stake domains...More>>
Publications & Demonstrators
All accepted publications from SPARTA partners under its funding as well as videos presenting some of the work done under SPARTA
Publications
Preprocessing Pipelines Including Block-Matching Convolutional Neural Network for Image Denoising to Robustify Deep Reidentification against Evasion Attacks
Marek Pawlicki, Ryszard S. Choraś
Artificial neural networks have become the go-to solution for computer vision tasks, including problems of the security domain. One such example comes in the form of reidentification, where deep learning can be part of the surveillance pipeline. The use case necessitates considering an adversarial setting—and neural networks have been shown...More>>
Domains: deep learning; computer vision; adversarial attacks; adversarial defences
Hybroid: Toward Android Malware Detection and Categorization with Program Code and Network Traffic
Mohammad Reza Norouzian, Peng Xu, Claudia Eckert, and Apostolis Zarras
Android malicious applications have become so sophisticated that they can bypass endpoint protection measures. Therefore, it is safe to admit that traditional anti-malware techniques have become cumbersome, thereby raising the need to develop efficient ways to detect Android malware. In this paper, we present Hybroid, a hybrid Android malware detection...More>>
Domains: Android, malware detection, F1-score, AUC
Development of the Information Security Management System Standard for Public Sector Organisations in Estonia
Mari Seeba, Raimundas Matulevičius, and Ilmar Toom
Standardisation gives us a common understanding or processes to do something in a commonly accepted way. In information security management, it means to achieve the appropriate security level in the context of known and unknown risks. Each government’s goal should be to provide digital services to its citizens with the...More>>
Domains: ISMS, Public Sector Organisations
Security Risk Estimation and Management in Autonomous Driving Vehicles
Abasi-amefon O. Affia, Raimundas Matulevičius, and Rando Tõnisson
Autonomous vehicles (AV) are intelligent information systems that perceive, collect, generate and disseminate information to improve knowledge to act autonomously and provide its required services of mobility, safety, and comfort to humans. This paper combines the security risk management (ISSRM) and operationally critical threat, asset, and vulnerability evaluation (OCTAVE allegro) methods...More>>
Domains: Autonomous vehicles, Self-driving cars, Security risk management, ISSRM, OCTAVE, Intelligent information systems
Information Security Analysis in the Passenger-Autonomous Vehicle Interaction
Mariia Bakhtina, Raimundas Matulevičius
Autonomous vehicles (AV) are becoming a part of humans’ everyday life. There are numerous pilot projects of driverless public buses; some car manufacturers deliver their premium-level automobiles with advanced self-driving features. Thus, assuring the security of a Passenger–Autonomous Vehicle interaction arises as an important research topic, as along with opportunities,...More>>
Domains: Autonomous vehicles
Risk-Oriented Design Approach For Forensic-Ready Software Systems
Lukas Daubner, Raimundas Matulevičius
Digital forensic investigation is a complex and time-consuming activity in response to a cybersecurity incident or cybercrime to answer questions related to it. These typically are what happened, when, where, how, and who is responsible. However, answering them is often very laborious and sometimes outright impossible due to a lack...More>>
Domains: Computing, Technology policy, Computer crime
A Novel Approach for Network Intrusion Detection Using Multistage Deep Learning Image Recognition
Toldinas, Jevgenijus, Algimantas Venčkauskas, Robertas Damaševičius, Šarūnas Grigaliūnas, Nerijus Morkevičius, and Edgaras Baranauskas
The current rise in hacking and computer network attacks throughout the world has heightened the demand for improved intrusion detection and prevention solutions. The intrusion detection system (IDS) is critical in identifying abnormalities and assaults on the network, which have grown in size and pervasiveness. The paper proposes a novel...More>>
Domains: network intrusion detection; deep learning; image representation
Method for Dynamic Service Orchestration in Fog Computing
Morkevicius, Nerijus, Algimantas Venčkauskas, Nerijus Šatkauskas, and Jevgenijus Toldinas
Fog computing is meant to deal with the problems which cloud computing cannot solve alone. As the fog is closer to a user, it can improve some very important QoS characteristics, such as a latency and availability. One of the challenges in the fog architecture is heterogeneous constrained devices and...More>>
Domains: QoS, Fog Computing