OnSt'16 - Online Safety, Trust and Fraud Prevention


Online Safety, Trust and Fraud Prevention


Motivation | Program

Important Dates Organizers | Program Committee

Contact: Dr. Marco Fisichella

E-Mail: marco@riskident.com

Motivation Overview

Almost every aspect of our lives is influenced by the web, such as in entertainment, education, health, commerce, the government, social interaction, and many more. The profound impact these recent changes have on our lives requires to rethink the way we make decisions in these areas.

Besides questions related to cost and benefit, there are important issues raised by users regarding trust and safety. Can I trust this service with my data? Is it safe to use? In many cases, trust-related issues become a deal-breaker for the adoption of online services. We commonly find cases where people avoid online banking or buying products online due to the fear of becoming prey of fraudulent activity. Thus, providing a trustworthy environment for users is of utmost importance.

When online fraud are committed, fraudsters take advantage of gaps allowing them to unjustifiably enrich themselves. However, when fighting fraud, companies face a dilemma, given that no system is perfect: In e-commerce, on the one hand, fraud and its related losses should be reduced on the other hand, users neither want to be accused of fraud nor treated like criminals. In other areas, such as health, the problems associated with data abuse and security leaks could even result in more severe damage than purely financial matters.

Yet, companies’ practical implementations of fraud investigation processes rarely meet scientific standards. Fraud prevention companies offer diverse products on the market, but neither their effectivity nor their efficiency has been verified scientifically until now. Dealing with these issues, the first step should be a clean definition of what constitutes fraud and how it can be measured. Afterwards, models can be built and tested according to scientific standards of evaluation. On this basis, a careful risk analysis can be conducted in order to weigh pros and cons of pursuing individual suspicious cases.

Companies spend millions to protect themselves from fraudulent activities. One of the most interesting aspects is the fact that fighting fraud is a social interaction that needs constant supervision and improvement: a never ending race between criminals and investigators, in which both actors adjust for the actions of the other.

This workshop aims at bringing together research from a wide array of disciplines (mathematics, computer science, economy, philosophy, social science) to (i) understand the cases and motivations of fraudulent activities in online environments, (ii) find solutions to detect and analyze fraud, and (iii) derive means to prevent it.

The OnST workshop focuses on online fraud detection and prevention, but submissions that tackle these challenges in other environments are welcomed as well. We invite the submission of on-going and mature research work with a particular focus on the following topics:

  • User Modeling and Personalization of Fraudulent and Malicious Users
  • Features Engineering in the Online Fraud Detection Domain
  • Outlier and Anomaly Detection
  • Fraud Rule Engine
  • Time-Series, Spatial-Based, Graph-Based, Spatio-Temporal Approaches
  • Fraud Detection in the Streaming Domain
  • Fraud Detection Applications
  • Distributed Fraud Detection Systems
  • IT-forensics

The main research questions that the workshop would like to answer are:

(i) What are the best practices for detecting fraudulent and malicious activities?

(ii) What are the best practices for preventing fraudulent and malicious activities?

(iii) Which is the psychological impact of fraudulent activities on the society?

We invite the submission of original work in these and related areas. Each submission to the workshop will be peer-reviewed by at least two expert reviewers.


Workshop Rationale and Significance and Relevance to WebSci

The proposed workshop has a strong relation to most topics of the main program of WebSci, such as “Crime on the Web and Security”, “Data Ethics, Privacy and Security”, and “Statistics on the Web”. As such, the workshop will be widely accessible to the WebSci community. At the same time, though, this workshop will approach the above WebSci topics from the unique and emerging viewpoint of detecting and preventing malicious activities from a scientific point of view, considering their psychological and , economical impact as well as their risk. This viewpoint and the workshop’s focus clearly differentiate the workshop from WebSci’s main program and make it an appealing addition to it.


Duration and Foreseen Workshop Format

Full-day workshop with about 10 accepted papers, 2 keynote talks (one putting more emphasis on an economic model for dealing with online fraud, and the second putting more emphasis on finding fraudulent connections using devices fingerprinting), 1 round-table discussion session. The first keynote speaker is already confirmed. She is Kristina Holstein, a product manager for Trust and Safety at mobile.de GmbH. A brief bio of Kristina Holstein:

Kristina Holstein is a product manager for Trust and Safety at mobile.de GmbH, the leading online automotive marketplace in Germany which operates as a subsidiary of eBay Inc. She has been with the company for over 10 years. She is leading the company ́s Trust and Safety team that helps build trust in the community through various educational resources, rules and policies, and trust-building programs, all of which help maintain general platform security and promote trustworthiness.


Submission guidelines

As input, we welcome position papers of 3-5 pages in the ACM SIG Proceedings format available at http://www.acm.org/publications/proceedings-template

Each accepted paper will be given a ten minute time slot for a lightning talk. After each talk, there will be time for discussion for up to 20 minutes.

Please submit your papers via Easychair: https://easychair.org/conferences/?conf=onst16



The workshop will be hold on the 22nd of May, starting at 1.00 pm:

– 1.00 – 1.15 pm: Welcome and Introduction

– 1.15 – 2.00 pm: Key Note – Building Trust in Automotive Marketplaces (Kristina Holstein)

– 2.00 – 2.45 pm: You Shall Not Pass: Detecting Malicious Users at Registration Time (Christian Kater and Robert Jäschke)

– 2.45 – 3.15 pm: Coffee Break

– 3.15 – 4.00 pm: Fraud Prevention by Connections Inference (Marco Fisichella)

– 4.00 – 4.30 pm: Discovering Credit Card Fraud Methods in Online Tutorials (Gert Jan van Hardeveld, Craig Webber and Kieron O’Hara)

– 4.30 – 5.15 pm: Your saving could be next: Fighting Fraud in Fintech (Kevin Scholz)


Important dates

Deadline for submissions: EXTENDED 25 March 2016

Notification of acceptance: EXTENDED 12 April 2016

Camera-ready:  17 April 2016

Workshop date: 22 May 2016, 1:00 PM – 5:30 PM


Workshop Organizers

Dr. Marco Fisichella is the head of the data science team at Risk.Ident (Otto group, Germany) where they devise algorithms in order to detect the online frauds. Before he joined Risk Ident, he was postdoctoral researcher at the L3S Research Center in Hannover, Germany. Until beginning of 2015, he was also lecturer of the Artificial Intelligence course for the Master in Computer Science at the Leibniz University of Hannover. His research interests include data mining, information retrieval, generative model, event detection, clustering methods based on statistical approaches, near duplicate detection. He has worked as project manager in several EU-funded projects including (1) DuraArk -Preservation of architectural building data, and (2) OpenScout – accelerating the use, improvement and distribution of open content in the field of management education and training. He actively participated as proposal consultant and advisory board member in the following accepted proposal: (1) ALEXANDRIA – an ERC Advanced Grant Project on Foundations for Temporal Retrieval, Exploration and Analytics in Web Archives (2) Zivile Sicherheit – a BMBF German funding program for tracking the Russian flu in U.S. and German medical and popular reports, occurred between 1889 and 1893. He has strong publication records in top-tier conferences, such as CIKM, SPIRE, ECIR and WISE and active professional memberships, i.e., invited reviewer and PC member (e.g., ICDM, WWW, and CIKM) and journal reviewer (e.g., Data & Knowledge Engineering Journal – Elsevier – on the track area about Reasoning Approaches). Finally, he received the best paper award at EC-TEL 2011 for his publication on “Unsupervised Auto-tagging for Learning Object Enrichment”.

Dr. Mario Elstner is a Senior Data Scientist & Engineer working at Risk.Ident GmbH, where he is responsible for the development and implementation of statistical models and algorithms that form the core of Risk Ident’s products for fraud prevention. His specialties include Machine Learning and Big Data Technologies. Before joining Risk.Ident, Dr. Elstner has been working as a Data Scientist & Big Data Analyst for a range of customers in the E-Commerce, Financial and Industrial sectors. He completed his Phd in Mathematical physics at the Technical University of Munich in 2011 with a thesis on non-relativistic quantum electrodynamics and published his scientific works in the Journals of “Mathematical Physics” and “Reviews in Mathematical Physics”.

Dr. Ricardo Kawase is a data analyst for the Trust and Safety team at mobile.de GmbH, the leading online automotive marketplace in Germany which operates as a subsidiary of eBay Inc. He has joined the mobile.de Trust and Safety team in February 2015, where his main role encompasses the understanding of user behavior in the platform in order to provide solid information to support product development in the domain of listing quality improvement the fraud prevention. Pior to that, he worked as a researcher at L3S Research Center Hannover, Germany for seven years. His main research interests are on the fiel of webscience, user modeling, personalization, crowdsourcing, and fraud detection. He has a strong research record with over 50 publications, including top-tier conferences such as SIGCHI, WWW, ISWC, ESWC, HYPERTEXT, UMAP. He additionally serves as a reviewer in several conferences and journals.

Tobias Knuth is a data scientist working for Risk.Ident and a lecturer at Hamburg School of Business Administration. His areas of interest cover machine learning, economics, and software engineering. In cooperation with Risk.Ident, he is currently enrolled in a doctorate programme at Edinburgh Napier University, working on his dissertation about utilising machine learning in e-commerce transaction fraud from an economic perspective.


Program Committee

  • Andrea Ceroni, L3S Research Center, Germany
  • Dr. Mario Elstner, Risk.Ident GmbH – Otto Group, Germany
  • Dr. Marco Fisichella, Risk.Ident GmbH – Otto Group, Germany
  • Dr. Ricardo Kawase, mobile.de – eBay Inc., Germany
  • Tobias Knuth, Risk.Ident GmbH, Edinburgh Napier University, Hamburg School of Business Administration – Otto Group, Germany
  • Ujwal Gadiraju, L3S Research Center, Germany
  • Prof. Dr. Rüdiger Grimm, Fellow of the German Informatics Society GI e.V.
  • Dr. Katja Niemann, Fraunhofer Institute for Applied Information Technology (FIT), Germany
  • Dr. Bernardo Pereira Nunes, Pontifical Catholic University of Rio de Janeiro – PUC-Rio, Brazil
  • Simon Schenk, Risk.Ident GmbH – Otto Group, Germany

The entire workshop will gain and leverage from the hard grounded experience of Prof. Dr. Rüdiger Grimm, who was also head of the research group “Security for Virtual Goods” of the Fraunhofer Institute for Digital Media Technology. Hereafter, his bio.

Prof. Dr. Rüdiger Grimm was professor for IT Risk Management at the University Koblenz-Landau since 2005-2015, and he is continuing research and teaching duties in his University after his retirement in October 2015. Since 2008 he was, and still is, a consulting researcher in Fraunhofer SIT, Darmstadt. He graduated in Mathematics from the University Göttingen in 1976 and worked thereafter until 1985 in different positions, as teacher in the German voluntary service in Tanzania, as IT scientist in Dresdner Bank Frankfurt, and in the University Computer Center Essen. 1985-2000 R. Grimm was computer scientist at GMD, which today is the Fraunhofer Institute of Secure IT Technology (SIT), Darmstadt. 2000-2005 he was professor for multimedia application systems at the University of Technology, Ilmenau. During that time, 2002-2005 he was also head of the research group “Security for Virtual Goods” of the Fraunhofer Institute for Digital Media Technology (IDMT) in Ilmenau. 2011-2014 he was elected Dean of the Faculty of Informatics in Koblenz. Since 2010 he is Fellow of the German Informatics Society GI e.V.