@inproceedings{35426, author = {{Richter, Cedric and Haltermann, Jan Frederik and Jakobs, Marie-Christine and Pauck, Felix and Schott, Stefan and Wehrheim, Heike}}, booktitle = {{37th IEEE/ACM International Conference on Automated Software Engineering}}, publisher = {{ACM}}, title = {{{Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs?}}}, doi = {{10.1145/3551349.3561156}}, year = {{2023}}, } @inproceedings{35427, author = {{Pauck, Felix}}, booktitle = {{37th IEEE/ACM International Conference on Automated Software Engineering}}, publisher = {{ACM}}, title = {{{Scaling Arbitrary Android App Analyses}}}, doi = {{10.1145/3551349.3561339}}, year = {{2023}}, } @inproceedings{44194, author = {{Ahmed, Qazi Arbab and Awais, Muhammad and Platzner, Marco}}, booktitle = {{The 24th International Symposium on Quality Electronic Design (ISQED'23), San Francisco, Califorina USA}}, location = {{San Fransico CA 94023-0607, USA}}, title = {{{MAAS: Hiding Trojans in Approximate Circuits}}}, year = {{2023}}, } @phdthesis{43108, author = {{Pauck, Felix}}, publisher = {{Paderborn University}}, title = {{{Cooperative Android App Analysis}}}, doi = {{10.17619/UNIPB/1-1698}}, year = {{2023}}, } @phdthesis{44323, abstract = {{Reading between the lines has so far been reserved for humans. The present dissertation addresses this research gap using machine learning methods. Implicit expressions are not comprehensible by computers and cannot be localized in the text. However, many texts arise on interpersonal topics that, unlike commercial evaluation texts, often imply information only by means of longer phrases. Examples are the kindness and the attentiveness of a doctor, which are only paraphrased (“he didn’t even look me in the eye”). The analysis of such data, especially the identification and localization of implicit statements, is a research gap (1). This work uses so-called Aspect-based Sentiment Analysis as a method for this purpose. It remains open how the aspect categories to be extracted can be discovered and thematically delineated based on the data (2). Furthermore, it is not yet explored how a collection of tools should look like, with which implicit phrases can be identified and thus made explicit (3). Last, it is an open question how to correlate the identified phrases from the text data with other data, including the investigation of the relationship between quantitative scores (e.g., school grades) and the thematically related text (4). Based on these research gaps, the research question is posed as follows: Using text mining methods, how can implicit rating content be properly interpreted and thus made explicit before it is automatically categorized and quantified? The uniqueness of this dissertation is based on the automated recognition of implicit linguistic statements alongside explicit statements. These are identified in unstructured text data so that features expressed only in the text can later be compared across data sources, even though they were not included in rating categories such as stars or school grades. German-language physician ratings from websites in three countries serve as the sample domain. The solution approach consists of data creation, a pipeline for text processing and analyses based on this. In the data creation, aspect classes are identified and delineated across platforms and marked in text data. This results in six datasets with over 70,000 annotated sentences and detailed guidelines. The models that were created based on the training data extract and categorize the aspects. In addition, the sentiment polarity and the evaluation weight, i. e., the importance of each phrase, are determined. The models, which are combined in a pipeline, are used in a prototype in the form of a web application. The analyses built on the pipeline quantify the rating contents by linking the obtained information with further data, thus allowing new insights. As a result, a toolbox is provided to identify quantifiable rating content and categories using text mining for a sample domain. This is used to evaluate the approach, which in principle can also be adapted to any other domain.}}, author = {{Kersting, Joschka}}, pages = {{208}}, publisher = {{Universität der Bundeswehr München }}, title = {{{Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining}}}, year = {{2023}}, } @inbook{45888, author = {{Wehrheim, Heike and Platzner, Marco and Bodden, Eric and Schubert, Philipp and Pauck, Felix and Jakobs, Marie-Christine}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{125--144}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Verifying Software and Reconfigurable Hardware Services}}}, doi = {{10.5281/zenodo.8068583}}, volume = {{412}}, year = {{2023}}, } @inbook{45882, author = {{Bäumer, Frederik Simon and Chen, Wei-Fan and Geierhos, Michaela and Kersting, Joschka and Wachsmuth, Henning}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{65--84}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Dialogue-based Requirement Compensation and Style-adjusted Data-to-text Generation}}}, doi = {{10.5281/zenodo.8068456}}, volume = {{412}}, year = {{2023}}, } @inbook{45884, author = {{Hanselle, Jonas Manuel and Hüllermeier, Eyke and Mohr, Felix and Ngonga Ngomo, Axel-Cyrille and Sherif, Mohamed and Tornede, Alexander and Wever, Marcel Dominik}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{85--104}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Configuration and Evaluation}}}, doi = {{10.5281/zenodo.8068466}}, volume = {{412}}, year = {{2023}}, } @inbook{45886, author = {{Wehrheim, Heike and Hüllermeier, Eyke and Becker, Steffen and Becker, Matthias and Richter, Cedric and Sharma, Arnab}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{105--123}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Composition Analysis in Unknown Contexts}}}, doi = {{10.5281/zenodo.8068510}}, volume = {{412}}, year = {{2023}}, } @inbook{46205, abstract = {{We present a concept for quantifying evaluative phrases to later compare rating texts numerically instead of just relying on stars or grades. We achievethis by combining deep learning models in an aspect-based sentiment analysis pipeline along with sentiment weighting, polarity, and correlation analyses that combine deep learning results with metadata. The results provide new insights for the medical field. Our application domain, physician reviews, shows that there are millions of review texts on the Internet that cannot yet be comprehensively analyzed because previous studies have focused on explicit aspects from other domains (e.g., products). We identify, extract, and classify implicit and explicit aspect phrases equally from German-language review texts. To do so, we annotated aspect phrases representing reviews on numerous aspects of a physician, medical practice, or practice staff. We apply the best performing transformer model, XLM-RoBERTa, to a large physician review dataset and correlate the results with existing metadata. As a result, we can show different correlations between the sentiment polarity of certain aspect classes (e.g., friendliness, practice equipment) and physicians’ professions (e.g., surgeon, ophthalmologist). As a result, we have individual numerical scores that contain a variety of information based on deep learning algorithms that extract textual (evaluative) information and metadata from the Web.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Data Management Technologies and Applications}}, editor = {{Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}}, isbn = {{9783031378898}}, issn = {{1865-0929}}, pages = {{45--65}}, publisher = {{Springer Nature Switzerland}}, title = {{{Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews}}}, doi = {{10.1007/978-3-031-37890-4_3}}, volume = {{1860}}, year = {{2023}}, } @phdthesis{45780, author = {{Tornede, Alexander}}, title = {{{Advanced Algorithm Selection with Machine Learning: Handling Large Algorithm Sets, Learning From Censored Data, and Simplyfing Meta Level Decisions}}}, doi = {{10.17619/UNIPB/1-1780 }}, year = {{2023}}, } @book{45863, abstract = {{In the proposal for our CRC in 2011, we formulated a vision of markets for IT services that describes an approach to the provision of such services that was novel at that time and, to a large extent, remains so today: „Our vision of on-the-fly computing is that of IT services individually and automatically configured and brought to execution from flexibly combinable services traded on markets. At the same time, we aim at organizing markets whose participants maintain a lively market of services through appropriate entrepreneurial actions.“ Over the last 12 years, we have developed methods and techniques to address problems critical to the convenient, efficient, and secure use of on-the-fly computing. Among other things, we have made the description of services more convenient by allowing natural language input, increased the quality of configured services through (natural language) interaction and more efficient configuration processes and analysis procedures, made the quality of (the products of) providers in the marketplace transparent through reputation systems, and increased the resource efficiency of execution through reconfigurable heterogeneous computing nodes and an integrated treatment of service description and configuration. We have also developed network infrastructures that have a high degree of adaptivity, scalability, efficiency, and reliability, and provide cryptographic guarantees of anonymity and security for market participants and their products and services. To demonstrate the pervasiveness of the OTF computing approach, we have implemented a proof-of-concept for OTF computing that can run typical scenarios of an OTF market. We illustrated the approach using a cutting-edge application scenario – automated machine learning (AutoML). Finally, we have been pushing our work for the perpetuation of On-The-Fly Computing beyond the SFB and sharing the expertise gained in the SFB in events with industry partners as well as transfer projects. This work required a broad spectrum of expertise. Computer scientists and economists with research interests such as computer networks and distributed algorithms, security and cryptography, software engineering and verification, configuration and machine learning, computer engineering and HPC, microeconomics and game theory, business informatics and management have successfully collaborated here.}}, author = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{247}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}}, doi = {{10.17619/UNIPB/1-1797}}, volume = {{412}}, year = {{2023}}, } @phdthesis{47833, author = {{König, Jürgen}}, title = {{{On the Membership and Correctness Problem for State Serializability and Value Opacity}}}, year = {{2023}}, } @inproceedings{29945, author = {{Witschen, Linus Matthias and Wiersema, Tobias and Reuter, Lucas David and Platzner, Marco}}, booktitle = {{2022 59th ACM/IEEE Design Automation Conference (DAC)}}, location = {{San Francisco, USA}}, title = {{{Search Space Characterization for Approximate Logic Synthesis }}}, year = {{2022}}, } @inproceedings{29865, author = {{Witschen, Linus Matthias and Wiersema, Tobias and Artmann, Matthias and Platzner, Marco}}, booktitle = {{Design, Automation and Test in Europe (DATE)}}, location = {{Online}}, title = {{{MUSCAT: MUS-based Circuit Approximation Technique}}}, year = {{2022}}, } @unpublished{30868, abstract = {{Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of AC problem variants and methods proposed in the literature. Existing reviews do not take into account all derivatives of the AC problem, nor do they offer a complete classification scheme. To this end, we introduce taxonomies to describe the AC problem and features of configuration methods, respectively. We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry. Finally, our review provides researchers and practitioners with a look at future research directions in the field of AC.}}, author = {{Schede, Elias and Brandt, Jasmin and Tornede, Alexander and Wever, Marcel Dominik and Bengs, Viktor and Hüllermeier, Eyke and Tierney, Kevin}}, booktitle = {{arXiv:2202.01651}}, title = {{{A Survey of Methods for Automated Algorithm Configuration}}}, year = {{2022}}, } @inproceedings{32311, abstract = {{Testing is one of the most frequent means of quality assurance for software. Property-based testing aims at generating test suites for checking code against user-defined properties. Test input generation is, however, most often independent of the property to be checked, and is instead based on random or user-defined data generation.In this paper, we present property-driven unit testing of functions with numerical inputs and outputs. Alike property-based testing, it allows users to define the properties to be tested for. Contrary to property-based testing, it also uses the property for a targeted generation of test inputs. Our approach is a form of learning-based testing where we first of all learn a model of a given black-box function using standard machine learning algorithms, and in a second step use model and property for test input generation. This allows us to test both predefined functions as well as machine learned regression models. Our experimental evaluation shows that our property-driven approach is more effective than standard property-based testing techniques.}}, author = {{Sharma, Arnab and Melnikov, Vitaly and Hüllermeier, Eyke and Wehrheim, Heike}}, booktitle = {{Proceedings of the 10th IEEE/ACM International Conference on Formal Methods in Software Engineering (FormaliSE)}}, pages = {{113--123}}, publisher = {{IEEE}}, title = {{{Property-Driven Testing of Black-Box Functions}}}, year = {{2022}}, } @inproceedings{34103, abstract = {{It is well known that different algorithms perform differently well on an instance of an algorithmic problem, motivating algorithm selection (AS): Given an instance of an algorithmic problem, which is the most suitable algorithm to solve it? As such, the AS problem has received considerable attention resulting in various approaches - many of which either solve a regression or ranking problem under the hood. Although both of these formulations yield very natural ways to tackle AS, they have considerable weaknesses. On the one hand, correctly predicting the performance of an algorithm on an instance is a sufficient, but not a necessary condition to produce a correct ranking over algorithms and in particular ranking the best algorithm first. On the other hand, classical ranking approaches often do not account for concrete performance values available in the training data, but only leverage rankings composed from such data. We propose HARRIS- Hybrid rAnking and RegRessIon foreSts - a new algorithm selector leveraging special forests, combining the strengths of both approaches while alleviating their weaknesses. HARRIS' decisions are based on a forest model, whose trees are created based on splits optimized on a hybrid ranking and regression loss function. As our preliminary experimental study on ASLib shows, HARRIS improves over standard algorithm selection approaches on some scenarios showing that combining ranking and regression in trees is indeed promising for AS.}}, author = {{Fehring, Lukass and Hanselle, Jonas Manuel and Tornede, Alexander}}, booktitle = {{Workshop on Meta-Learning (MetaLearn 2022) @ NeurIPS 2022}}, location = {{Baltimore}}, title = {{{HARRIS: Hybrid Ranking and Regression Forests for Algorithm Selection}}}, year = {{2022}}, } @article{30511, abstract = {{AbstractMany critical codebases are written in C, and most of them use preprocessor directives to encode variability, effectively encoding software product lines. These preprocessor directives, however, challenge any static code analysis. SPLlift, a previously presented approach for analyzing software product lines, is limited to Java programs that use a rather simple feature encoding and to analysis problems with a finite and ideally small domain. Other approaches that allow the analysis of real-world C software product lines use special-purpose analyses, preventing the reuse of existing analysis infrastructures and ignoring the progress made by the static analysis community. This work presents VarAlyzer, a novel static analysis approach for software product lines. VarAlyzer first transforms preprocessor constructs to plain C while preserving their variability and semantics. It then solves any given distributive analysis problem on transformed product lines in a variability-aware manner. VarAlyzer ’s analysis results are annotated with feature constraints that encode in which configurations each result holds. Our experiments with 95 compilation units of OpenSSL show that applying VarAlyzer enables one to conduct inter-procedural, flow-, field- and context-sensitive data-flow analyses on entire product lines for the first time, outperforming the product-based approach for highly-configurable systems.}}, author = {{Schubert, Philipp and Gazzillo, Paul and Patterson, Zach and Braha, Julian and Schiebel, Fabian and Hermann, Ben and Wei, Shiyi and Bodden, Eric}}, issn = {{0928-8910}}, journal = {{Automated Software Engineering}}, keywords = {{inter-procedural static analysis, software product lines, preprocessor, LLVM, C/C++}}, number = {{1}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Static data-flow analysis for software product lines in C}}}, doi = {{10.1007/s10515-022-00333-1}}, volume = {{29}}, year = {{2022}}, } @inproceedings{32590, author = {{Richter, Cedric and Wehrheim, Heike}}, booktitle = {{2022 IEEE Conference on Software Testing, Verification and Validation (ICST)}}, pages = {{162--173}}, title = {{{Learning Realistic Mutations: Bug Creation for Neural Bug Detectors}}}, doi = {{10.1109/ICST53961.2022.00027}}, year = {{2022}}, }