@article{SchlierkampThurner2015,
  author    = {Schlierkamp, Kathrin and Thurner, Veronika},
  title     = {Was will ich eigentlich hier?},
  series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  volume    = {2015},
  journal   = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  number    = {9},
  editor    = {Schubert, Sigrid and Schwill, Andreas},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84748},
  pages     = {179 -- 187},
  year      = {2015},
  abstract  = {Die Wahl des richtigen Studienfaches und die daran anschließende Studieneingangsphase sind oft entscheidend f{\"u}r den erfolgreichen Verlauf eines Studiums. Eine große Herausforderung besteht dabei darin, bereits in den ersten Wochen des Studiums bestehende Defizite in vermeintlich einfachen Schl{\"u}sselkompetenzen zu erkennen und diese so bald wie m{\"o}glich zu beheben. Eine zweite, nicht minder wichtige Herausforderung ist es, m{\"o}glichst fr{\"u}hzeitig f{\"u}r jeden einzelnen Studierenden zu erkennen, ob er bzw. sie das individuell richtige Studienfach gew{\"a}hlt hat, das den jeweiligen pers{\"o}nlichen Neigungen, Interessen und F{\"a}higkeiten entspricht und zur Verwirklichung der eigenen Lebensziele beitr{\"a}gt. Denn nur dann sind Studierende ausreichend stark und dauerhaft intrinsisch motiviert, um ein anspruchsvolles, komplexes Studium erfolgreich durchzuziehen. In diesem Beitrag fokussieren wir eine Maßnahme, die die Studierenden an einen Prozess zur systematischen Reflexion des eigenen Lernprozesses und der eigenen Ziele heranf{\"u}hrt und beides in Relation setzt.},
  language  = {de}
}
@article{VossebergCzernikErbetal.2015,
  author    = {Vosseberg, Karin and Czernik, Sofie and Erb, Ulrike and Vielhaber, Michael},
  title     = {Projektorientierte Studieneingangsphase},
  series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  volume    = {2015},
  journal   = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  number    = {9},
  editor    = {Schubert, Sigrid and Schwill, Andreas},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84730},
  pages     = {169 -- 177},
  year      = {2015},
  abstract  = {Ziel einer neuen Studieneingangsphase ist, den Studierenden bis zum Ende des ersten Semesters ein vielf{\"a}ltiges Berufsbild der Informatik und Wirtschaftsinformatik mit dem breiten Aufgabenspektrum aufzubl{\"a}ttern und damit die Zusammenh{\"a}nge zwischen den einzelnen Modulen des Curriculums zu verdeutlichen. Die Studierenden sollen in die Lage versetzt werden, sehr eigenst{\"a}ndig die Planung und Gestaltung ihres Studiums in die Hand zu nehmen.},
  language  = {de}
}
@article{Broeker2015,
  author    = {Br{\"o}ker, Kathrin},
  title     = {Unterst{\"u}tzung Informatik-Studierender durch ein Lernzentrum},
  series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  volume    = {2015},
  journal   = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  number    = {9},
  editor    = {Schubert, Sigrid and Schwill, Andreas},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84754},
  pages     = {189 -- 197},
  year      = {2015},
  abstract  = {In diesem Papier wird das Konzept eines Lernzentrums f{\"u}r die Informatik (LZI) an der Universit{\"a}t Paderborn vorgestellt. Ausgehend von den fachspezifischen Schwierigkeiten der Informatik Studierenden werden die Angebote des LZIs erl{\"a}utert, die sich {\"u}ber die vier Bereiche Individuelle Beratung und Betreuung, „Offener Lernraum", Workshops und Lehrveranstaltungen sowie Forschung erstrecken. Eine erste Evaluation mittels Feedbackb{\"o}gen zeigt, dass das Angebot bei den Studierenden positiv aufgenommen wird. Zuk{\"u}nftig soll das Angebot des LZIs weiter ausgebaut und verbessert werden. Ausgangsbasis dazu sind weitere Studien.},
  language  = {de}
}
@phdthesis{Prasse2016,
  author    = {Prasse, Paul},
  title     = {Pattern recognition for computer security},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100251},
  school      = {Universit{\"a}t Potsdam},
  pages     = {VI, 75},
  year      = {2016},
  abstract  = {Computer Security deals with the detection and mitigation of threats to computer networks, data, and computing hardware. This thesis addresses the following two computer security problems: email spam campaign and malware detection. Email spam campaigns can easily be generated using popular dissemination tools by specifying simple grammars that serve as message templates. A grammar is disseminated to nodes of a bot net, the nodes create messages by instantiating the grammar at random. Email spam campaigns can encompass huge data volumes and therefore pose a threat to the stability of the infrastructure of email service providers that have to store them. Malware -software that serves a malicious purpose- is affecting web servers, client computers via active content, and client computers through executable files. Without the help of malware detection systems it would be easy for malware creators to collect sensitive information or to infiltrate computers. The detection of threats -such as email-spam messages, phishing messages, or malware- is an adversarial and therefore intrinsically difficult problem. Threats vary greatly and evolve over time. The detection of threats based on manually-designed rules is therefore difficult and requires a constant engineering effort. Machine-learning is a research area that revolves around the analysis of data and the discovery of patterns that describe aspects of the data. Discriminative learning methods extract prediction models from data that are optimized to predict a target attribute as accurately as possible. Machine-learning methods hold the promise of automatically identifying patterns that robustly and accurately detect threats. This thesis focuses on the design and analysis of discriminative learning methods for the two computer-security problems under investigation: email-campaign and malware detection. The first part of this thesis addresses email-campaign detection. We focus on regular expressions as a syntactic framework, because regular expressions are intuitively comprehensible by security engineers and administrators, and they can be applied as a detection mechanism in an extremely efficient manner. In this setting, a prediction model is provided with exemplary messages from an email-spam campaign. The prediction model has to generate a regular expression that reveals the syntactic pattern that underlies the entire campaign, and that a security engineers finds comprehensible and feels confident enough to use the expression to blacklist further messages at the email server. We model this problem as two-stage learning problem with structured input and output spaces which can be solved using standard cutting plane methods. Therefore we develop an appropriate loss function, and derive a decoder for the resulting optimization problem. The second part of this thesis deals with the problem of predicting whether a given JavaScript or PHP file is malicious or benign. Recent malware analysis techniques use static or dynamic features, or both. In fully dynamic analysis, the software or script is executed and observed for malicious behavior in a sandbox environment. By contrast, static analysis is based on features that can be extracted directly from the program file. In order to bypass static detection mechanisms, code obfuscation techniques are used to spread a malicious program file in many different syntactic variants. Deobfuscating the code before applying a static classifier can be subjected to mostly static code analysis and can overcome the problem of obfuscated malicious code, but on the other hand increases the computational costs of malware detection by an order of magnitude. In this thesis we present a cascaded architecture in which a classifier first performs a static analysis of the original code and -based on the outcome of this first classification step- the code may be deobfuscated and classified again. We explore several types of features including token \$n\$-grams, orthogonal sparse bigrams, subroutine-hashings, and syntax-tree features and study the robustness of detection methods and feature types against the evolution of malware over time. The developed tool scans very large file collections quickly and accurately. Each model is evaluated on real-world data and compared to reference methods. Our approach of inferring regular expressions to filter emails belonging to an email spam campaigns leads to models with a high true-positive rate at a very low false-positive rate that is an order of magnitude lower than that of a commercial content-based filter. Our presented system -REx-SVMshort- is being used by a commercial email service provider and complements content-based and IP-address based filtering. Our cascaded malware detection system is evaluated on a high-quality data set of almost 400,000 conspicuous PHP files and a collection of more than 1,00,000 JavaScript files. From our case study we can conclude that our system can quickly and accurately process large data collections at a low false-positive rate.},
  language  = {en}
}
@phdthesis{Videla2014,
  author    = {Videla, Santiago},
  title     = {Reasoning on the response of logical signaling networks with answer set programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71890},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Deciphering the functioning of biological networks is one of the central tasks in systems biology. In particular, signal transduction networks are crucial for the understanding of the cellular response to external and internal perturbations. Importantly, in order to cope with the complexity of these networks, mathematical and computational modeling is required. We propose a computational modeling framework in order to achieve more robust discoveries in the context of logical signaling networks. More precisely, we focus on modeling the response of logical signaling networks by means of automated reasoning using Answer Set Programming (ASP). ASP provides a declarative language for modeling various knowledge representation and reasoning problems. Moreover, available ASP solvers provide several reasoning modes for assessing the multitude of answer sets. Therefore, leveraging its rich modeling language and its highly efficient solving capacities, we use ASP to address three challenging problems in the context of logical signaling networks: learning of (Boolean) logical networks, experimental design, and identification of intervention strategies. Overall, the contribution of this thesis is three-fold. Firstly, we introduce a mathematical framework for characterizing and reasoning on the response of logical signaling networks. Secondly, we contribute to a growing list of successful applications of ASP in systems biology. Thirdly, we present a software providing a complete pipeline for automated reasoning on the response of logical signaling networks.},
  language  = {en}
}
@article{WesselsMetzger2015,
  author    = {Weßels, Doris and Metzger, Christiane},
  title     = {Die Arbeitswelt im Fokus},
  series = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  volume    = {2015},
  journal   = {HDI 2014 : Gestalten von {\"U}berg{\"a}ngen},
  number    = {9},
  editor    = {Schwill, Andreas and Schubert, Sigrid},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-80289},
  pages     = {77 -- 92},
  year      = {2015},
  abstract  = {F{\"u}r Bachelor-Studierende der Wirtschaftsinformatik im zweiten Semester an der Fachhochschule Kiel werden im Modul Informationsmanagement neben klassischen didaktischen Ans{\"a}tzen in einer seminaristischen Unterrichtsform so genannte „Aktivbausteine" eingesetzt: Studierende erhalten zum einen die Gelegenheit, sich im Kontakt mit Fach- und F{\"u}hrungskr{\"a}ften aus der Industrie ein konkretes Bild vom Beruf der Wirtschaftsinformatikerin bzw. des Wirtschaftsinformatikers zu machen; zum anderen erarbeiten sie innovative Ans{\"a}tze der Prozessverbesserung aus Sicht der IT oder mit Nutzenpotenzial f{\"u}r die IT und pr{\"a}sentieren ihre Ergebnisse {\"o}ffentlich im Rahmen des Kieler Prozessmanagementforums. Diese Aktivbausteine dienen insbesondere der Berufsfeldorientierung: Durch die Informationen, die die Studierenden {\"u}ber die Anforderungen und T{\"a}tigkeiten von im Beruf stehenden Menschen erhalten, werden sie in die Lage versetzt, fundierte Entscheidungen bzgl. ihrer Studiengestaltung und Berufswahl zu treffen. Im Beitrag wird die Konzeption der Bausteine vorgestellt und deren Grad der Zielerreichung durch aktuelle Evaluationsergebnisse erl{\"a}utert. Zudem wird die motivationale Wirkung der Aktivbausteine anhand der Theorie der Selbstbestimmung von Deci und Ryan [DR1985, DR1993, DR2004] erl{\"a}utert.},
  language  = {de}
}
@phdthesis{Haider2013,
  author    = {Haider, Peter},
  title     = {Prediction with Mixture Models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69617},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Learning a model for the relationship between the attributes and the annotated labels of data examples serves two purposes. Firstly, it enables the prediction of the label for examples without annotation. Secondly, the parameters of the model can provide useful insights into the structure of the data. If the data has an inherent partitioned structure, it is natural to mirror this structure in the model. Such mixture models predict by combining the individual predictions generated by the mixture components which correspond to the partitions in the data. Often the partitioned structure is latent, and has to be inferred when learning the mixture model. Directly evaluating the accuracy of the inferred partition structure is, in many cases, impossible because the ground truth cannot be obtained for comparison. However it can be assessed indirectly by measuring the prediction accuracy of the mixture model that arises from it. This thesis addresses the interplay between the improvement of predictive accuracy by uncovering latent cluster structure in data, and further addresses the validation of the estimated structure by measuring the accuracy of the resulting predictive model. In the application of filtering unsolicited emails, the emails in the training set are latently clustered into advertisement campaigns. Uncovering this latent structure allows filtering of future emails with very low false positive rates. In order to model the cluster structure, a Bayesian clustering model for dependent binary features is developed in this thesis. Knowing the clustering of emails into campaigns can also aid in uncovering which emails have been sent on behalf of the same network of captured hosts, so-called botnets. This association of emails to networks is another layer of latent clustering. Uncovering this latent structure allows service providers to further increase the accuracy of email filtering and to effectively defend against distributed denial-of-service attacks. To this end, a discriminative clustering model is derived in this thesis that is based on the graph of observed emails. The partitionings inferred using this model are evaluated through their capacity to predict the campaigns of new emails. Furthermore, when classifying the content of emails, statistical information about the sending server can be valuable. Learning a model that is able to make use of it requires training data that includes server statistics. In order to also use training data where the server statistics are missing, a model that is a mixture over potentially all substitutions thereof is developed. Another application is to predict the navigation behavior of the users of a website. Here, there is no a priori partitioning of the users into clusters, but to understand different usage scenarios and design different layouts for them, imposing a partitioning is necessary. The presented approach simultaneously optimizes the discriminative as well as the predictive power of the clusters. Each model is evaluated on real-world data and compared to baseline methods. The results show that explicitly modeling the assumptions about the latent cluster structure leads to improved predictions compared to the baselines. It is beneficial to incorporate a small number of hyperparameters that can be tuned to yield the best predictions in cases where the prediction accuracy can not be optimized directly.},
  language  = {en}
}
@phdthesis{Dick2016,
  author    = {Dick, Uwe},
  title     = {Discriminative Classification Models for Internet Security},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-102593},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 57},
  year      = {2016},
  abstract  = {Services that operate over the Internet are under constant threat of being exposed to fraudulent use. Maintaining good user experience for legitimate users often requires the classification of entities as malicious or legitimate in order to initiate countermeasures. As an example, inbound email spam filters decide for spam or non-spam. They can base their decision on both the content of each email as well as on features that summarize prior emails received from the sending server. In general, discriminative classification methods learn to distinguish positive from negative entities. Each decision for a label may be based on features of the entity and related entities. When labels of related entities have strong interdependencies---as can be assumed e.g. for emails being delivered by the same user---classification decisions should not be made independently and dependencies should be modeled in the decision function. This thesis addresses the formulation of discriminative classification problems that are tailored for the specific demands of the following three Internet security applications. Theoretical and algorithmic solutions are devised to protect an email service against flooding of user inboxes, to mitigate abusive usage of outbound email servers, and to protect web servers against distributed denial of service attacks. In the application of filtering an inbound email stream for unsolicited emails, utilizing features that go beyond each individual email's content can be valuable. Information about each sending mail server can be aggregated over time and may help in identifying unwanted emails. However, while this information will be available to the deployed email filter, some parts of the training data that are compiled by third party providers may not contain this information. The missing features have to be estimated at training time in order to learn a classification model. In this thesis an algorithm is derived that learns a decision function that integrates over a distribution of values for each missing entry. The distribution of missing values is a free parameter that is optimized to learn an optimal decision function. The outbound stream of emails of an email service provider can be separated by the customer IDs that ask for delivery. All emails that are sent by the same ID in the same period of time are related, both in content and in label. Hijacked customer accounts may send batches of unsolicited emails to other email providers, which in turn might blacklist the sender's email servers after detection of incoming spam emails. The risk of being blocked from further delivery depends on the rate of outgoing unwanted emails and the duration of high spam sending rates. An optimization problem is developed that minimizes the expected cost for the email provider by learning a decision function that assigns a limit on the sending rate to customers based on the each customer's email stream. Identifying attacking IPs during HTTP-level DDoS attacks allows to block those IPs from further accessing the web servers. DDoS attacks are usually carried out by infected clients that are members of the same botnet and show similar traffic patterns. HTTP-level attacks aim at exhausting one or more resources of the web server infrastructure, such as CPU time. If the joint set of attackers cannot increase resource usage close to the maximum capacity, no effect will be experienced by legitimate users of hosted web sites. However, if the additional load raises the computational burden towards the critical range, user experience will degrade until service may be unavailable altogether. As the loss of missing one attacker depends on block decisions for other attackers---if most other attackers are detected, not blocking one client will likely not be harmful---a structured output model has to be learned. In this thesis an algorithm is developed that learns a structured prediction decoder that searches the space of label assignments, guided by a policy. Each model is evaluated on real-world data and is compared to reference methods. The results show that modeling each classification problem according to the specific demands of the task improves performance over solutions that do not consider the constraints inherent to an application.},
  language  = {en}
}
@phdthesis{AlAreqi2017,
  author    = {Al-Areqi, Samih Taha Mohammed},
  title     = {Semantics-based automatic geospatial service composition},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-402616},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvi, 163},
  year      = {2017},
  abstract  = {Although it has become common practice to build applications based on the reuse of existing components or services, technical complexity and semantic challenges constitute barriers to ensuring a successful and wide reuse of components and services. In the geospatial application domain, the barriers are self-evident due to heterogeneous geographic data, a lack of interoperability and complex analysis processes. Constructing workflows manually and discovering proper services and data that match user intents and preferences is difficult and time-consuming especially for users who are not trained in software development. Furthermore, considering the multi-objective nature of environmental modeling for the assessment of climate change impacts and the various types of geospatial data (e.g., formats, scales, and georeferencing systems) increases the complexity challenges. Automatic service composition approaches that provide semantics-based assistance in the process of workflow design have proven to be a solution to overcome these challenges and have become a frequent demand especially by end users who are not IT experts. In this light, the major contributions of this thesis are: (i) Simplification of service reuse and workflow design of applications for climate impact analysis by following the eXtreme Model-Driven Development (XMDD) paradigm. (ii) Design of a semantic domain model for climate impact analysis applications that comprises specifically designed services, ontologies that provide domain-specific vocabulary for referring to types and services, and the input/output annotation of the services using the terms defined in the ontologies. (iii) Application of a constraint-driven method for the automatic composition of workflows for analyzing the impacts of sea-level rise. The application scenario demonstrates the impact of domain modeling decisions on the results and the performance of the synthesis algorithm.},
  language  = {en}
}
@article{Rolf2010,
  author    = {Rolf, Arno},
  title     = {Themeng{\"a}rten in der Informatik-Ausbildung},
  series = {Commentarii informaticae didacticae : (CID)},
  journal   = {Commentarii informaticae didacticae : (CID)},
  number    = {4},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  issn      = {1868-0844},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64281},
  pages     = {7 -- 12},
  year      = {2010},
  abstract  = {Die M{\"o}glichkeiten sich zu informieren, am Leben der vielen Anderen teilzunehmen ist durch das Internet mit seinen Tweets, Google-Angeboten und sozialen Netzwerken wie Facebook ins Unermessliche gewachsen. Zugleich f{\"u}hlen sich viele Nutzer {\"u}berfordert und meinen, im Meer der Informationen zu ertrinken. So bekennt Frank Schirrmacher in seinem Buch Payback, dass er den geistigen Anforderungen unserer Zeit nicht mehr gewachsen ist. Sein Kopf komme nicht mehr mit. Er sei unkonzentriert, vergesslich und st{\"a}ndig abgelenkt. Das, was vielen zum Problem geworden ist, sehen viele Studierende eher pragmatisch. Der Wissenserwerb in Zeiten von Internet und E-Learning l{\"a}uft an Hochschulen h{\"a}ufig nach der Helene-Hegemann-Methode ab: Zun{\"a}chst machen sich die Studierenden, z.B. im Rahmen einer Studien- oder Hausarbeit, bei Wikipedia „schlau", ein Einstieg ist geschafft. Anschließend wird dieses Wissen mit Google angereichert. Damit ist {\"U}berblickswissen vorhanden. Mit geschickter copy-and-paste-Komposition l{\"a}sst sich daraus schon ein „Werk" erstellen. Der ein oder andere Studierende gibt sich mit diesem Wissenserwerb zufrieden und bricht seinen Lernprozess hier bereits ab. Nun ist zwar am Ende jeder Studierende f{\"u}r seinen Wissenserwerb selbst verantwortlich. Die erkennbar unbefriedigende Situation sollte die Hochschulen aber herausfordern, das Internet in Vorlesungen und Seminaren auszuprobieren und sinnvolle Anwendungen zu entwickeln. Beispiele gibt es durchaus. Unter der Metapher E-Learning hat sich ein umfangreicher Forschungsschwerpunkt an den Universit{\"a}ten entwickelt. Einige Beispiele von vielen: So hat der Osnabr{\"u}cker Informatik-Professor Oliver Vornberger seine Vorlesungen als Video ins Netz gestellt. Per RSS ist es m{\"o}glich, Sequenzen aufs iPod zu laden. Die {\"u}bliche Dozentenangst, dann w{\"u}rden sie ja vor leeren B{\"a}nken sitzen, scheint unbegr{\"u}ndet. Sie werden von den Studierenden vor allem zur Pr{\"u}fungsvorbereitung genutzt. Wie ist das Internet, das f{\"u}r die junge Generation zu einem alles andere verdr{\"a}ngenden Universalmedium geworden ist, didaktisch in die Hochschullehre einzubinden? Wie also ist konkret mit diesen Herausforderungen umzugehen? Dies soll uns im Folgenden besch{\"a}ftigen.},
  language  = {de}
}