@article{PrasseKnaebelMachlicaetal.2019,
  author    = {Prasse, Paul and Knaebel, Rene and Machlica, Lukas and Pevny, Tomas and Scheffer, Tobias},
  title     = {Joint detection of malicious domains and infected clients},
  series = {Machine learning},
  volume    = {108},
  journal   = {Machine learning},
  number    = {8-9},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0885-6125},
  doi       = {10.1007/s10994-019-05789-z},
  pages     = {1353 -- 1368},
  year      = {2019},
  abstract  = {Detection of malware-infected computers and detection of malicious web domains based on their encrypted HTTPS traffic are challenging problems, because only addresses, timestamps, and data volumes are observable. The detection problems are coupled, because infected clients tend to interact with malicious domains. Traffic data can be collected at a large scale, and antivirus tools can be used to identify infected clients in retrospect. Domains, by contrast, have to be labeled individually after forensic analysis. We explore transfer learning based on sluice networks; this allows the detection models to bootstrap each other. In a large-scale experimental study, we find that the model outperforms known reference models and detects previously unknown malware, previously unknown malware families, and previously unknown malicious domains.},
  language  = {en}
}
@article{PrasseIversenLienhardetal.2022,
  author    = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Herwig, Ralf and Scheffer, Tobias},
  title     = {Pre-Training on In Vitro and Fine-Tuning on Patient-Derived Data Improves Deep Neural Networks for Anti-Cancer Drug-Sensitivity Prediction},
  series = {MDPI},
  volume    = {14},
  journal   = {MDPI},
  edition   = {16},
  publisher = {MDPI},
  address   = {Basel, Schweiz},
  issn      = {2072-6694},
  doi       = {10.3390/cancers14163950},
  pages     = {1 -- 14},
  year      = {2022},
  abstract  = {Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models' accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.},
  language  = {en}
}
@unpublished{PrasseGrubenMachlikaetal.2016,
  author    = {Prasse, Paul and Gruben, Gerrit and Machlika, Lukas and Pevny, Tomas and Sofka, Michal and Scheffer, Tobias},
  title     = {Malware Detection by HTTPS Traffic Analysis},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100942},
  pages     = {10},
  year      = {2016},
  abstract  = {In order to evade detection by network-traffic analysis, a growing proportion of malware uses the encrypted HTTPS protocol. We explore the problem of detecting malware on client computers based on HTTPS traffic analysis. In this setting, malware has to be detected based on the host IP address, ports, timestamp, and data volume information of TCP/IP packets that are sent and received by all the applications on the client. We develop a scalable protocol that allows us to collect network flows of known malicious and benign applications as training data and derive a malware-detection method based on a neural networks and sequence classification. We study the method's ability to detect known and new, unknown malware in a large-scale empirical study.},
  language  = {en}
}
@misc{PrasseIversenLienhardetal.2022,
  author    = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Herwig, Ralf and Scheffer, Tobias},
  title     = {Pre-Training on In Vitro and Fine-Tuning on Patient-Derived Data Improves Deep Neural Networks for Anti-Cancer Drug-Sensitivity Prediction},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-57734},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-577341},
  pages     = {1 -- 14},
  year      = {2022},
  abstract  = {Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models' accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.},
  language  = {en}
}
@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}
}
@article{PrasseIversenLienhardetal.2022,
  author    = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Bauer, Christopher and Herwig, Ralf and Scheffer, Tobias},
  title     = {Matching anticancer compounds and tumor cell lines by neural networks with ranking loss},
  series = {NAR: genomics and bioinformatics},
  volume    = {4},
  journal   = {NAR: genomics and bioinformatics},
  number    = {1},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {2631-9268},
  doi       = {10.1093/nargab/lqab128},
  pages     = {10},
  year      = {2022},
  abstract  = {Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drug components that are likely to achieve the highest efficacy for a cancer cell line at hand at a therapeutic dose. State of the art drug sensitivity models use regression techniques to predict the inhibitory concentration of a drug for a tumor cell line. This regression objective is not directly aligned with either of these principal goals of drug sensitivity models: We argue that drug sensitivity modeling should be seen as a ranking problem with an optimization criterion that quantifies a drug's inhibitory capacity for the cancer cell line at hand relative to its toxicity for healthy cells. We derive an extension to the well-established drug sensitivity regression model PaccMann that employs a ranking loss and focuses on the ratio of inhibitory concentration and therapeutic dosage range. We find that the ranking extension significantly enhances the model's capability to identify the most effective anticancer drugs for unseen tumor cell profiles based in on in-vitro data.},
  language  = {en}
}
@article{BauerHerwigLienhardetal.2021,
  author    = {Bauer, Chris and Herwig, Ralf and Lienhard, Matthias and Prasse, Paul and Scheffer, Tobias and Schuchhardt, Johannes},
  title     = {Large-scale literature mining to assess the relation between anti-cancer drugs and cancer types},
  series = {Journal of translational medicine},
  volume    = {19},
  journal   = {Journal of translational medicine},
  number    = {1},
  publisher = {BioMed Central},
  address   = {London},
  issn      = {1479-5876},
  doi       = {10.1186/s12967-021-02941-z},
  pages     = {13},
  year      = {2021},
  abstract  = {Background: There is a huge body of scientific literature describing the relation between tumor types and anti-cancer drugs. The vast amount of scientific literature makes it impossible for researchers and physicians to extract all relevant information manually. Methods: In order to cope with the large amount of literature we applied an automated text mining approach to assess the relations between 30 most frequent cancer types and 270 anti-cancer drugs. We applied two different approaches, a classical text mining based on named entity recognition and an AI-based approach employing word embeddings. The consistency of literature mining results was validated with 3 independent methods: first, using data from FDA approvals, second, using experimentally measured IC-50 cell line data and third, using clinical patient survival data. Results: We demonstrated that the automated text mining was able to successfully assess the relation between cancer types and anti-cancer drugs. All validation methods showed a good correspondence between the results from literature mining and independent confirmatory approaches. The relation between most frequent cancer types and drugs employed for their treatment were visualized in a large heatmap. All results are accessible in an interactive web-based knowledge base using the following link: . Conclusions: Our approach is able to assess the relations between compounds and cancer types in an automated manner. Both, cancer types and compounds could be grouped into different clusters. Researchers can use the interactive knowledge base to inspect the presented results and follow their own research questions, for example the identification of novel indication areas for known drugs.},
  language  = {en}
}