David Stutz (PhD Student)

Personal Information

About Me | Blog | CV | GitHub | LinkedIn | Google Scholar

Bachelor/master theses available; topics on adversarial robustness — robustness of deep neural networks against adversarial examples.

Publications

2024

  1. Conference paper
    D2
    “On Adversarial Training without Perturbing all Examples,” in The Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 2024.

2023

  1. Conference paper
    D2
    “Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  2. Conference paper
    D2
    “Robustifying Token Attention for Vision Transformers,” in IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, 2023.
  3. Article
    D2
    “Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 3, 2023.
  4. Conference paper
    D2
    “Certified Robust Models with Slack Control and Large Lipschitz Constants,” in Pattern Recognition (DAGM GCPR 2023), Heidelberg, Germany, 2023.

2022

  1. Conference paper
    D2
    “Improving Robustness by Enhancing Weak Subnets,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  2. Thesis
    D2IMPR-CS
    “Understanding and Improving Robustness and Uncertainty Estimation in Deep Learning,” Universität des Saarlandes, Saarbrücken, 2022.
  3. Paper
    D2
    “On Fragile Features and Batch Normalization in Adversarial Training,” 2022. [Online]. Available: https://arxiv.org/abs/2204.12393.

2021

  1. Conference paper
    D2
    “Relating Adversarially Robust Generalization to Flat Minima,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  2. Conference paper
    D2
    “Bit Error Robustness for Energy-Efficient DNN Accelerators,” in Proceedings of the 4th MLSys Conference, Virtual Conference, 2021.

2020

  1. Conference paper
    D4D2
    “Adversarial Training Against Location-Optimized Adversarial Patches,” in Computer Vision -- ECCV Workshops 2020, Glasgow, UK, 2021.
  2. Conference paper
    D2
    “Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks,” in Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Virtual Conference, 2020.

2019

  1. Conference paper
    D2
    “Disentangling Adversarial Robustness and Generalization,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA, 2019.
  2. Paper
    D2
    “Confidence-Calibrated Adversarial Training and Detection: More Robust Models Generalizing Beyond the Attack Used During Training,” 2019. [Online]. Available: http://arxiv.org/abs/1910.06259.

2018

  1. Conference paper
    D2
    “Learning 3D Shape Completion from Laser Scan Data with Weak Supervision,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, USA, 2018.
  2. Article
    D2
    “Learning 3D Shape Completion under Weak Supervision,” International Journal of Computer Vision, vol. 128, 2018.