KBKonstantin Böttinger

Konstantin Böttinger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Konstantin Böttinger has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Societal Frameworks Can Improve LLM Alignment

    by Karolina Stańczak, Nicholas Meade, Mehar Bhatia, Hattie Zhou, Konstantin Böttinger, Jeremy Barnes, Jason Stanley, Nicolas Papernot, Nicolas Chapados, Denis Therien, et al.


  • Open Access

    GhosTEE: An Approach to Solving the GPU-Privacy Trade-off for Machine Learning Inference

    by Andrei-Cosmin Aprodu, Hendrik Meyer Zum Felde, Daniel Kowatsch, Konstantin Böttinger

  • Near Real-Time Detection and Rectification of Adversarial Patches

    by Ching-Yu Kao, Iheb Ghanmi, Houcemeddine Ben Ayed, Ayush Kumar, Konstantin Böttinger


  • Open Access

    Imbalance in Regression Datasets

    by Daniel Kowatsch, Nicolas M. Müller, Kilian Tscharke, Philip Sperl, Konstantin Bötinger

    For classification, the problem of class imbalance is well known and has been extensively studied. In this paper, we argue that imbalance in regression is an equally important problem which has so far been overlooked: Due to under- and over-representations in a data set's target distribution, regressors are prone to degenerate to naive models, systematically neglecting uncommon training data and over-representing targets seen often during training. We analyse this problem theoretically and use resulting insights to develop a first definition of imbalance in regression, which we show to be a generalisation of the commonly employed imbalance measure in classification. With this, we hope to turn the spotlight on the overlooked problem of imbalance in regression and to provide common ground for future research.


  • Open Access

    Physical Adversarial Examples for Multi-Camera Systems

    by Ana Răduţoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

    Neural networks build the foundation of several intelligent systems, which, however, are known to be easily fooled by adversarial examples. Recent advances made these attacks possible even in air-gapped scenarios, where the autonomous system observes its surroundings by, e.g., a camera. We extend these ideas in our research and evaluate the robustness of multi-camera setups against such physical adversarial examples. This scenario becomes ever more important with the rise in popularity of autonomous vehicles, which fuse the information of several cameras for their driving decision. While we find that multi-camera setups provide some robustness towards past attack methods, we see that this advantage reduces when optimizing on multiple perspectives at once. We propose a novel attack method that we call Transcender-MC, where we incorporate online 3D renderings and perspective projections in the training process. Moreover, we motivate that certain data augmentation techniques can facilitate the generation of successful adversarial examples even further. Transcender-MC is 11% more effective in successfully attacking multi-camera setups than state-of-the-art methods. Our findings offer valuable insights regarding the resilience of object detection in a setup with multiple cameras and motivate the need of developing adequate defense mechanisms against them.

  • Open Access

    Localized Shortcut Removal

    by Nicolas M. Müller, Jochen Jacobs, Jennifer Williams, Konstantin Böttinger

    Machine learning is a data-driven field, and the quality of the underlying datasets plays a crucial role in learning success. However, high performance on held-out test data does not necessarily indicate that a model generalizes or learns anything meaningful. This is often due to the existence of machine learning shortcuts - features in the data that are predictive but unrelated to the problem at hand. To address this issue for datasets where the shortcuts are smaller and more localized than true features, we propose a novel approach to detect and remove them. We use an adversarially trained lens to detect and eliminate highly predictive but semantically unconnected clues in images. In our experiments on both synthetic and real-world data, we show that our proposed approach reliably identifies and neutralizes such shortcuts without causing degradation of model performance on clean data. We believe that our approach can lead to more meaningful and generalizable machine learning models, especially in scenarios where the quality of the underlying datasets is crucial.

  • R2-AD2: Detecting Anomalies by Analysing the Raw Gradient

    by Jan-Philipp Schulze, Philip Sperl, Ana Răduțoiu, Carla Sagebiel, Konstantin Böttinger


  • Open Access

    Defending Against Adversarial Denial-of-Service Data Poisoning Attacks

    by Nicolas M. Müller, Simon Roschmann, Konstantin Böttinger

    Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into the training dataset to degrade the performance of machine learning models. As recent work has shown, such Denial-of-Service (DoS) data poisoning attacks are highly effective. To mitigate this threat, we propose a new approach of detecting DoS poisoned instances. In comparison to related work, we deviate from clustering and anomaly detection based approaches, which often suffer from the curse of dimensionality and arbitrary anomaly threshold selection. Rather, our defence is based on extracting information from the training data in such a generalized manner that we can identify poisoned samples based on the information present in the unpoisoned portion of the data. We evaluate our defence against two DoS poisoning attacks and seven datasets, and find that it reliably identifies poisoned instances. In comparison to related work, our defence improves false positive / false negative rates by at least 50%, often more.

  • DA3G: Detecting Adversarial Attacks by Analysing Gradients

    by Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger


  • Robuste Lernverfahren

    by Karla Markert, Konstantin Böttinger