2024
Oedingen, Marc; Engelhardt, Raphael C.; Denz, Robin; Hammer, Maximilian; Konen, Wolfgang
ChatGPT Code Detection: Techniques for Uncovering the Source of Code Miscellaneous
2024.
Links | BibTeX | Schlagwörter: AI, ChatGPT, Code Detection, Large Language Models, machine learning
@misc{Oedingen2024,
title = {ChatGPT Code Detection: Techniques for Uncovering the Source of Code},
author = {Marc Oedingen and Raphael C. Engelhardt and Robin Denz and Maximilian Hammer and Wolfgang Konen},
url = {https://arxiv.org/abs/2405.15512},
year = {2024},
date = {2024-05-01},
urldate = {2024-01-01},
journal = {arXiv preprint arXiv:2405.15512},
keywords = {AI, ChatGPT, Code Detection, Large Language Models, machine learning},
pubstate = {published},
tppubtype = {misc}
}
Oedingen, Marc; Engelhardt, Raphael C.; Denz, Robin; Hammer, Maximilian; Konen, Wolfgang
ChatGPT Code Detection: Techniques for Uncovering the Source of Code Journal Article
In: AI, vol. 5, no. 3, S. 1066–1094, 2024, ISSN: 2673-2688.
Abstract | Links | BibTeX | Schlagwörter: AI, ChatGPT, Code Detection, Large Language Models, machine learning
@article{Oedingen2024_AI,
title = {ChatGPT Code Detection: Techniques for Uncovering the Source of Code},
author = {Marc Oedingen and Raphael C. Engelhardt and Robin Denz and Maximilian Hammer and Wolfgang Konen},
url = {https://www.mdpi.com/2673-2688/5/3/53},
doi = {10.3390/ai5030053},
issn = {2673-2688},
year = {2024},
date = {2024-05-01},
urldate = {2024-01-01},
journal = {AI},
volume = {5},
number = {3},
pages = {1066–1094},
abstract = {In recent times, large language models (LLMs) have made significant strides in generating computer code, blurring the lines between code created by humans and code produced by artificial intelligence (AI). As these technologies evolve rapidly, it is crucial to explore how they influence code generation, especially given the risk of misuse in areas such as higher education. The present paper explores this issue by using advanced classification techniques to differentiate between code written by humans and code generated by ChatGPT, a type of LLM. We employ a new approach that combines powerful embedding features (black-box) with supervised learning algorithms including Deep Neural Networks, Random Forests, and Extreme Gradient Boosting to achieve this differentiation with an impressive accuracy of 98%. For the successful combinations, we also examine their model calibration, showing that some of the models are extremely well calibrated. Additionally, we present white-box features and an interpretable Bayes classifier to elucidate critical differences between the code sources, enhancing the explainability and transparency of our approach. Both approaches work well, but provide at most 85–88% accuracy. Tests on a small sample of untrained humans suggest that humans do not solve the task much better than random guessing. This study is crucial in understanding and mitigating the potential risks associated with using AI in code generation, particularly in the context of higher education, software development, and competitive programming.},
keywords = {AI, ChatGPT, Code Detection, Large Language Models, machine learning},
pubstate = {published},
tppubtype = {article}
}
2023
Engelhardt, Raphael C; Oedingen, Marc; Lange, Moritz; Wiskott, Laurenz; Konen, Wolfgang
Iterative Oblique Decision Trees Deliver Explainable RL Models Journal Article
In: Algorithms, vol. 16, no. 6, S. 282, 2023.
Links | BibTeX | Schlagwörter: AI, decision trees, deep learning, explainable AI, reinforcement learning, RL3
@article{Engelhardt2023,
title = {Iterative Oblique Decision Trees Deliver Explainable RL Models},
author = {Raphael C Engelhardt and Marc Oedingen and Moritz Lange and Laurenz Wiskott and Wolfgang Konen},
url = {https://www.mdpi.com/1999-4893/16/6/282},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Algorithms},
volume = {16},
number = {6},
pages = {282},
publisher = {MDPI},
keywords = {AI, decision trees, deep learning, explainable AI, reinforcement learning, RL3},
pubstate = {published},
tppubtype = {article}
}
Suchfeld
Albers, Alexander
Der Einfluss einer intuitiveren graphischen UI und weiteren spielunterstützenden Features auf den Spielerfolg und Spielspaß im Spiel Ökolopoly Masters Thesis
TH Köln – University of Applied Sciences, 2024, (Bachelor thesis).
@mastersthesis{Albers2024,
title = {Der Einfluss einer intuitiveren graphischen UI und weiteren spielunterstützenden Features auf den Spielerfolg und Spielspaß im Spiel Ökolopoly },
author = {Alexander Albers},
year = {2024},
date = {2024-12-01},
school = {TH Köln – University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Langrehr, Sarah
ChatGPT als Mathematik-Lernbegleiter – Wie unterstützen ChatGPT 3.5, 4.0 und 4.0 + WolframAlpha Schüler und Studierende im Lernprozess? Masters Thesis
TH Köln – University of Applied Sciences, 2024, (Bachelor thesis).
@mastersthesis{Langrehr2024,
title = {ChatGPT als Mathematik-Lernbegleiter – Wie unterstützen ChatGPT 3.5, 4.0 und 4.0 + WolframAlpha Schüler und Studierende im Lernprozess? },
author = {Sarah Langrehr},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA_SLangrehr_ChatGPT-final.pdf},
year = {2024},
date = {2024-10-01},
school = {TH Köln – University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Marcus, Tobias
Untersuchung von stochastischen und nicht-stochastischen Reinforcement-Learning-Algorithmen für Blackjack und Kuhn Poker Masters Thesis
TH Köln – University of Applied Sciences, 2024, (Bachelor thesis).
@mastersthesis{Marcus2024,
title = {Untersuchung von stochastischen und nicht-stochastischen Reinforcement-Learning-Algorithmen für Blackjack und Kuhn Poker },
author = {Tobias Marcus},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-TMarcus2024-final.pdf},
year = {2024},
date = {2024-07-01},
school = {TH Köln – University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Oedingen, Marc; Engelhardt, Raphael C.; Denz, Robin; Hammer, Maximilian; Konen, Wolfgang
ChatGPT Code Detection: Techniques for Uncovering the Source of Code Miscellaneous
2024.
@misc{Oedingen2024,
title = {ChatGPT Code Detection: Techniques for Uncovering the Source of Code},
author = {Marc Oedingen and Raphael C. Engelhardt and Robin Denz and Maximilian Hammer and Wolfgang Konen},
url = {https://arxiv.org/abs/2405.15512},
year = {2024},
date = {2024-05-01},
urldate = {2024-01-01},
journal = {arXiv preprint arXiv:2405.15512},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Oedingen, Marc; Engelhardt, Raphael C.; Denz, Robin; Hammer, Maximilian; Konen, Wolfgang
ChatGPT Code Detection: Techniques for Uncovering the Source of Code Journal Article
In: AI, vol. 5, no. 3, S. 1066–1094, 2024, ISSN: 2673-2688.
@article{Oedingen2024_AI,
title = {ChatGPT Code Detection: Techniques for Uncovering the Source of Code},
author = {Marc Oedingen and Raphael C. Engelhardt and Robin Denz and Maximilian Hammer and Wolfgang Konen},
url = {https://www.mdpi.com/2673-2688/5/3/53},
doi = {10.3390/ai5030053},
issn = {2673-2688},
year = {2024},
date = {2024-05-01},
urldate = {2024-01-01},
journal = {AI},
volume = {5},
number = {3},
pages = {1066–1094},
abstract = {In recent times, large language models (LLMs) have made significant strides in generating computer code, blurring the lines between code created by humans and code produced by artificial intelligence (AI). As these technologies evolve rapidly, it is crucial to explore how they influence code generation, especially given the risk of misuse in areas such as higher education. The present paper explores this issue by using advanced classification techniques to differentiate between code written by humans and code generated by ChatGPT, a type of LLM. We employ a new approach that combines powerful embedding features (black-box) with supervised learning algorithms including Deep Neural Networks, Random Forests, and Extreme Gradient Boosting to achieve this differentiation with an impressive accuracy of 98%. For the successful combinations, we also examine their model calibration, showing that some of the models are extremely well calibrated. Additionally, we present white-box features and an interpretable Bayes classifier to elucidate critical differences between the code sources, enhancing the explainability and transparency of our approach. Both approaches work well, but provide at most 85–88% accuracy. Tests on a small sample of untrained humans suggest that humans do not solve the task much better than random guessing. This study is crucial in understanding and mitigating the potential risks associated with using AI in code generation, particularly in the context of higher education, software development, and competitive programming.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Paul, Jonathan
Untersuchung über die Eignung von KI-Modellen als Tutor in der Mathematikausbildung Masters Thesis
TH Köln – University of Applied Sciences, 2024, (Bachelor thesis).
@mastersthesis{Paul2024,
title = {Untersuchung über die Eignung von KI-Modellen als Tutor in der Mathematikausbildung},
author = {Jonathan Paul},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-JPaul2024-final.pdf},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-01},
school = {TH Köln – University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Engelhardt, Raphael C; Oedingen, Marc; Lange, Moritz; Wiskott, Laurenz; Konen, Wolfgang
Iterative Oblique Decision Trees Deliver Explainable RL Models Journal Article
In: Algorithms, vol. 16, no. 6, S. 282, 2023.
@article{Engelhardt2023,
title = {Iterative Oblique Decision Trees Deliver Explainable RL Models},
author = {Raphael C Engelhardt and Marc Oedingen and Moritz Lange and Laurenz Wiskott and Wolfgang Konen},
url = {https://www.mdpi.com/1999-4893/16/6/282},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Algorithms},
volume = {16},
number = {6},
pages = {282},
publisher = {MDPI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fabig, Niklas
Reinforcement Learning für Standard Operating Procedures einer Atomkraftwerkssimulation Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Master thesis).
@mastersthesis{Fabig2022,
title = {Reinforcement Learning für Standard Operating Procedures einer Atomkraftwerkssimulation},
author = {Niklas Fabig},
year = {2022},
date = {2022-08-01},
urldate = {2022-08-01},
school = {TH Köln -- University of Applied Sciences},
note = {Master thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Weitz, Ann
Untersuchung von selbstlernenden Reinforcement Learning Agenten im computergenerierten Spiel Yavalath Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Bachelor thesis).
@mastersthesis{Weitz2022b,
title = {Untersuchung von selbstlernenden Reinforcement Learning Agenten im computergenerierten Spiel Yavalath},
author = {Ann Weitz},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-Weitz-final-2022.pdf},
year = {2022},
date = {2022-05-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Berner, Lukas
LSTM-Netze in der Echtzeit-Gelenkwinkelbestimmung auf Basis von EMG-Sensoren mit einem im Cross-Platform-Framework MediaPipe erstellten Trainingsdatensatz Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Bachelor thesis).
@mastersthesis{Berner2022,
title = {LSTM-Netze in der Echtzeit-Gelenkwinkelbestimmung auf Basis von EMG-Sensoren mit einem im Cross-Platform-Framework MediaPipe erstellten Trainingsdatensatz},
author = {Lukas Berner},
year = {2022},
date = {2022-02-01},
urldate = {2022-02-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
