Hello, We have submitted a paper: “Security Risk Management in Autonomous Driving Vehicles: Architecture Perspective” to NordSec2020 <https://nordsec2020.on.liu.se>. Co-authors: Rando Tõnisson, Raimundas Matulevičius, and Abasi-Amefon O. Affia (University of Tartu) Abstract: Security risk management is an important activity in engineering autonomous vehicles (AV). For autonomous driving service providers, it is necessary to explain what risks exist in the system and how they could be mitigated. Security risk management methods allow system stakeholders to manage the security risks within their systems. Unfortunately, an accepted standard to carry out security risk management, specifically for autonomous vehicles, is not presented in the reviewed literature. In this paper, we explore how to protect AV systems against the security risks and focus on the architectural perspective of such systems. To target the problem we security risk management (ISSRM) and operationally critical threat, asset and vulnerability evaluation (OCTAVE allegro) methods to define and estimate the AV protected asset, risk and risk treatment means. Our approach consists of a literaure study, case analysis, and interview of AV experts. The finding can be helpful to the AV engineers and security analysis to support the rationale for the decisions about the AV security investment. The research done is in the scope of WP6, task 6.5. If paper is accepted we will acknowledge the SPARTA project. Best greetings, Raimundas

Dear all, We are submitting a paper “Ensemble Based Classification using Neural Networks and Machine Learning Models for Windows PE Malware Detection” to the journal Electronics MDPI. The paper’s abstract is below. If accepted we will acknowledge SPARTA. The authors are Robertas Damaševičius, Algimantas Venčkauskas, Jevgenijus Toldinas, Šarūnas Grigaliūnas. All the best, Algimantas Venčkauskas ______________________________________________________ Abstract: Security of information is one of the greatest challenges facing organizations and institutions. Cybercrime is rising in frequency and magnitude in recent years with new ways to steal, change, destroy information or disable the information system appearing every day. One of the types of penetration into the information system where confidential information is processed is malware. An attacker injects malware into a computer system, after which he has full or partial access to critical information in the information system. This paper proposes an ensemble classification-based methodology for malware detection. The first-stage classification is performed by a stacked ensemble of dense (fully connected) and convolutional neural networks (CNN), while the final stage classification is performed by a meta-learner. For a meta-learner, we explored and compared 14 classifiers. For a baseline comparison, 13 machine learning methods are used: K-Nearest Neighbors, Linear Support Vector Machine (SVM), RBF SVM, Random Forest, AdaBoost, Decision Tree, ExtraTrees, Linear Discriminant Analysis, Logistic, Neural Net, Passive Classifier, Ridge Classifier, and Stochastic Gradient Descent classifier. We present the results of experiments performed on the Classification of Malware with PE headers (ClaMP) dataset. The best performance was achieved by an ensemble of five dense and CNN neural networks, and the ExtraTrees classifier as a meta-learner.

Dear all, I am happy to announce that our paper is accepted at the CAiSE 2021 Forum and will be printed in the Forum post-proceedings. We will acknowledge SPARTA and we will share the CRC of the paper once ready (a bit later this year :-)) Best greetings, Raimundas %———————%———————%———————- On 27. Feb 2021, at 22:25, CAiSE 2021 <caise21@easychair.org<mailto:caise21@easychair.org>> wrote: Dear Abasi-Amefon Affia, Raimundas Matulevicius, Rando Tonisson Thank you for submitting the paper "Security Risk Estimation and Management in Autonomous Driving Vehicles" to CAiSE 2021. <...> there was consensus that your paper fits well into the objectives of the CAiSE Forum, which is also a part of the CAiSE conference. So, we happily invite you to submit your paper for presentation at the CAiSE Forum. https://caise21.org/caise-forum/ <…> %———————%———————%——————— On 5. Dec 2020, at 00:55, Raimundas Matulevicius <raimundas.matulevicius@ut.ee<mailto:raimundas.matulevicius@ut.ee>> wrote: Dear all, Today we are submitting a paper “Security Risk Estimation and Measurement in Autonomous Driving Vehicles” to the CAiSE 2021 conference <https://caise21.org<https://caise21.org/>>. The paper’s abstract is below. If accepted we will acknowledge SPARTA. The authors are Abasi-amefon O. Affia, Raimundas Matulevičius and Rando Tõnisson from the University of Tartu, Estonia. All the best, Raimundas %———————%———————%——————— Abstract: Development of secure, intelligent information system (IIS) challenges organisation's business goals and budget constraints. This could potentially results in a limited mitigation of security risks. Furthermore, for the autonomous driving service providers, it becomes necessary to explain security risk impact and its mitigation means. In this paper, we explore how to protect components of the autonomous vehicle system. We employ the security risk management (ISSRM) and operationally critical threat, asset and vulnerability evaluation (OCTAVE allegro) methods to define and estimate the AV protected assets, risks and risk treatment decisions. In the context of IIS, our findings can support the AV engineers and security analysts when making decisions regarding security investment in the AV systems. -------- Information Security Research Group: <https://infosec.cs.ut.ee<https://infosec.cs.ut.ee/>> -------- Dr. Raimundas Matulevičius, Professor of Information Security Institute of Computer Science University of Tartu Narva mnt 18, 51009 Tartu Estonia