Portrait de Leo Schwinn

Leo Schwinn

Visiteur de recherche indépendant - Technical Univeristy of Munich
Superviseur⋅e principal⋅e
Gauthier Gidel
Sujets de recherche
Apprentissage profond
Site web
Google Scholar
GitHub

Publications

Raising the Bar for Certified Adversarial Robustness with Diffusion Models
Thomas Altstidl
David Dobre
Bjoern Eskofier
Gauthier Gidel
Leo Schwinn
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirica… (voir plus)l methods such as adversarial training, whose effectiveness is often later reduced by unseen attacks. Still, the limited certified robustness that is currently achievable has been a bottleneck for their practical adoption. Gowal et al. and Wang et al. have shown that generating additional training data using state-of-the-art diffusion models can considerably improve the robustness of adversarial training. In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses. In addition, we provide a list of recommendations to scale the robustness of certified training approaches. One of our main insights is that the generalization gap, i.e., the difference between the training and test accuracy of the original model, is a good predictor of the magnitude of the robustness improvement when using additional generated data. Our approach achieves state-of-the-art deterministic robustness certificates on CIFAR-10 for the
2023-05-16
ArXiv (prépublication)
doi.org
arxiv.org
Simulating Human Gaze with Neural Visual Attention
Leo Schwinn
Doina Precup
Bjoern Eskofier
Dario Zanca
2022-10-19
NeurIPS.cc/2022/Workshop/GMML (présentation orale)
doi.org
openreview.net
Behind the Machine's Gaze: Biologically Constrained Neural Networks Exhibit Human-like Visual Attention
Leo Schwinn
Doina Precup
B. Eskofier
Dario Zanca
.
2021-12-31
arXiv.org (prépublication)
doi.org
Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention
Leo Schwinn
Doina Precup
Bjoern Eskofier
Dario Zanca
By and large, existing computational models of visual attention tacitly assume perfect vision and full access to the stimulus and thereby de… (voir plus)viate from foveated biological vision. Moreover, modeling top-down attention is generally reduced to the integration of semantic features without incorporating the signal of a high-level visual tasks that have been shown to partially guide human attention. We propose the Neural Visual Attention (NeVA) algorithm to generate visual scanpaths in a top-down manner. With our method, we explore the ability of neural networks on which we impose a biologically-inspired foveated vision constraint to generate human-like scanpaths without directly training for this objective. The loss of a neural network performing a downstream visual task (i.e., classification or reconstruction) flexibly provides top-down guidance to the scanpath. Extensive experiments show that our method outperforms state-of-the-art unsupervised human attention models in terms of similarity to human scanpaths. Additionally, the flexibility of the framework allows to quantitatively investigate the role of different tasks in the generated visual behaviors. Finally, we demonstrate the superiority of the approach in a novel experiment that investigates the utility of scanpaths in real-world applications, where imperfect viewing conditions are given.
2021-12-31
Trans. Mach. Learn. Res. (publié)
openreview.net
openreview.net
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
Leo Schwinn
Leon Bungert
A. Nguyen
Ren'e Raab
Falk Pulsmeyer
Doina Precup
B. Eskofier
Dario Zanca
The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improvin… (voir plus)g the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural adversarial examples) or worst-case distribution shifts (e.g., optimized adversarial examples). In this work, we propose the Decision Region Quantification (DRQ) algorithm to improve the robustness of any differentiable pre-trained model against both real-world and worst-case distribution shifts in the data. DRQ analyzes the robustness of local decision regions in the vicinity of a given data point to make more reliable predictions. We theoretically motivate the DRQ algorithm by showing that it effectively smooths spurious local extrema in the decision surface. Furthermore, we propose an implementation using targeted and untargeted adversarial attacks. An extensive empirical evaluation shows that DRQ increases the robustness of adversarially and non-adversarially trained models against real-world and worst-case distribution shifts on several computer vision benchmark datasets.
2021-12-31
ICML (publié)
doi.org
proceedings.mlr.press