2022 IEEE CSR Workshop on Data Science for Cyber Security (DS4CS)

July 27, 2022

Over the years cyber-threats have increased in numbers and sophistication; adversaries now use a vast set of tools and tactics to attack their victims with their motivations ranging from intelligence collection to destruction or financial gain. Lately, the introduction of IoT devices on a number of applications, ranging from home automation to monitoring of critical infrastructures, has created an even more complicated cyber-defense landscape. The sheer number of IoT devices deployed globally, most of which are readily accessible and easily hacked, allows threat actors to use them as the cyber-weapon delivery system of choice in many today’s cyber-attacks, ranging from botnet-building for DDoS attacks, to malware spreading and spamming.

Staying on top of these evolving cyber-threats has become an increasingly difficult task that nowadays entails the collection, analysis, and leveraging of huge volumes of data and requires methodologies and techniques located at the intersection of statistics, data mining, machine learning, visualization and big data. Although the application of Data Science methodology to the Cyber Security domain is a relative new topic, it steadily gathers the interest of the research community as showcased by the utilization of data science techniques in a variety of cyber-defense facets that include proactive technologies (e.g., cyber-threat intelligence gathering and sharing), platform profiling (e.g., trust calculation and blacklisting), attack detection/mitigation (e.g., active network monitoring, situational awareness, and adaptable mitigation strategies), and others. This workshop aims to spotlight cutting-edge research in data science driven cyber-security in academia, business and government, as well as help in the alignment of these endeavors.

Topics of Interest

Prospective authors are encouraged to submit previously unpublished contributions from a broad range of topics, which include but are not limited to the following:

› Big data-driven cyber-security (incl. analytics, management)
› Machine and deep learning methods for cyber-security (incl. malware/phishing/botnet/ spam/intrusion/anomaly detection)
› Visualization methods (incl. visual situation awareness, VR & AR visualization, real-time visualization)
› AI-driven cybersecurity

› Private information retrieval
› Cyber-threat intelligence collection, identification and sharing at scale
› Private/sensitive information protection
› Machine-learning powered traffic analysis and attack modelling
› Machine learning-based platform profiling and trust management
› Advanced attack detection and mitigation

Important Dates

Paper submission deadline: April 22 May 27, 2022 AoE
Authors’ notification: May 13 June 23, 2022 AoE
Camera-ready submission: May 27 June 30, 2022 AoE
Early registration deadline: June 24 June 30, 2022 AoE
Workshop date: July 27, 2022

Submission Guidelines

The workshop’s proceedings will be published by IEEE and will be included in IEEE Xplore. The guidelines for authors, manuscript preparation guidelines, and policies of the IEEE CSR conference are applicable to DS4CS 2022 workshop. Please visit the authors’ instructions page for more details. When submitting your manuscript via the conference management system, please make sure that the workshop’s track 2T4 DS4CS is selected in the Topic Areas drop down list.

Workshop Committees

Workshop chairs

Christos Tryfonopoulos, University of the Peloponnese (GR)
Spiros Skiadopoulos, University of the Peloponnese (GR)
Angelos Marnerides, University of Glasgow (UK)

Publicity chair

Paraskevi Raftopoulou, University of the Peloponnese (GR)

Contact us


Program committee

Christos Anagnostopoulos, University of Glasgow (UK)
Avi Arampatzis, Democritus University of Thrace (GR)
Denilson Barbosa, University of Alberta (CA)
Srikanta Bedathur, IIT Delhi (IN)
Theodore Dalamagas, Athena Research Center (GR)
Christos Dimitrakakis, University of Oslo (NO)
Gabriel Ghinita, University of Massachusetts at Boston (US)
Aris Gkoulalas-Divanis, IBM Watson (US)
Christos Iliou, Centre for Research and Technology (GR); Bournemouth University (UK)
Anish Jindal, University of Durham (UK)
Mouna Kacimi, Free University of Bozen-Bolzano (IT)
Panos Kalnis, King Abdullah University of Science and Technology (SA)
Gjergji Kasneci, University of Tübingen (DE)
George Kollios, Boston University (US)
George Lepouras, University of the Peloponnese (GR)
Dongzhu Liu, University of Glasgow (UK)
Ida Mele, IASI-CNR (IT)
Dimitris Michail, Harokopio University of Athens (GR)
Luis Munoz Gonzalez, Imperial College London (UK)
Kim Pecina, DIaLOGIKa GmbH (DE)
Nikos Platis, University of the Peloponnese (GR)
Panagiotis Rizomiliotis, Harokopio University of Athens (GR)
Alkis Simitsis, Athena Research Center (GR)
Marco Squarcina, TU Wien (AT)
Nguyen Truong, University of Glasgow (UK)
Theodora Tsikrika, Centre for Research and Technology (GR)
Ioannis Tsimperidis, Democritus University of Thrace (GR)
Thanasis Vergoulis, Athena Research Center (GR)

Program Information

Wednesday, July 27

10:00–11:40 CET

Technical session WS-DS4CS-1

Chair: C. Tryfonopoulos, University of the Peloponnese (GR)
Room: Nafsika


Welcome by the DS4CS Chairs

C. Tryfonopoulos, S. Skiadopoulos, and A. Marnerides


Invited talk: AI: Ultimate threat or ultimate solution to cyber challenges?

Andreas Mauthe, Professor IT & Date Security, University Koblenz-Landau

Abstract. AI in Cyber Security has been discussed for a number of years, different Ai techniques have been deployed and AI has a prominent role within the entire Cyber ecosystem. This has been motivated by the strive towards more flexible and adaptable IT security, concepts such as networked systems resilience moving away from traditional “walled security” approaches, and the demand for more autonomous and decentralised solutions in systems, networking and security. The threat landscape has also changed, which demands to react to challenges quicker and also be able to detect the onset of unknown attacks and to react to them in a timely fashion, even before their cause might have been fully established. AI has been playing a key role as general enabler of novel Cyber Systems but also in providing new techniques to help to protect these systems from various threats and intrusions. However, AI itself has come under threat since AI based systems have shown bias, produced unexplainable or questionable results and can be prone to manipulation. Moreover, it has been shown that AI based systems can been deliberately attacked in the different phases of their life- and deployment cycle. Hence its use within Cyber Security has now also been put into question because of these security and resilience issues. Within the talk we explore the role of AI in Cyber Security, discuss its benefits but also show where there are challenges that might not be easily overcome.

Biography. Andreas Mauthe is a Professor IT & Date Security at the University Koblenz-Landau and Visiting Professor at Lancaster University, where he worked as academic till 2018. His research focus is security and resilience in networked systems (e.g. Clouds, SCADA, Smart Grids, ICS, etc.), Cyber security, and the use of AI in security. He has been working on issues related to cyber security for more than 15 years. The research in this field involves the use of AI based approaches for anomaly detection and policy-based mitigation to counter the onset of challenges and improve the security of network systems. Recently Andreas has also started research on the security of AI methods themselves, specifically machine learning. The focus here is on how the manipulation of machine learning methods (i.e. Adversarial Attacks) can be detected, prevented an mitigated. Andreas has published more than 150 peer-reviewed scientific papers, and is member if various programme committees, editorial boards and advisory groups.


Employing social network analysis to dark web communities

S. Nikoletos and P. Raftopoulou


Phishing detection using machine learning algorithm

J. Tanimu and S. Shiaeles

11:40–12:00 CET

Coffee break

12.00–13:20 CET

Technical session WS-DS4CS-2

Chair: C. Tryfonopoulos, University of the Peloponnese (GR)
Room: Nafsika


Machine learning-based ransomware detection using low-level memory access patterns obtained from live-forensic hypervisor

M. Hirano and R. Kobayashi


A Bayesian model combination based approach to active malware analysis

A. Hota and J. Schonwalder


A comprehensive API call analysis for detecting Windows-based ransomware

P. Mohan Anand, P. V. Sai Charan, and S. K. Shukla