Refine
Document Type
- Article (reviewed) (2) (remove)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- yes (2) (remove)
Keywords
- Adversarial robustness (1)
- Aliasing (1)
- CNNs (1)
- Deep Leaning (1)
- Roubst overfitting (1)
Institute
Open Access
- Open Access (2)
- Bronze (1)
- Hybrid (1)
Neural networks tend to overfit the training distribution and perform poorly on out-ofdistribution data. A conceptually simple solution lies in adversarial training, which introduces worst-case perturbations into the training data and thus improves model generalization to some extent. However, it is only one ingredient towards generally more robust models and requires knowledge about the potential attacks or inference time data corruptions during model training. This paper focuses on the native robustness of models that can learn robust behavior directly from conventional training data without out-of-distribution examples. To this end, we study the frequencies in learned convolution filters. Clean-trained models often prioritize high-frequency information, whereas adversarial training enforces models to shift the focus to low-frequency details during training. By mimicking this behavior through frequency regularization in learned convolution weights, we achieve improved native robustness to adversarial attacks, common corruptions, and other out-of-distribution tests. Additionally, this method leads to more favorable shifts in decision-making towards low-frequency information, such as shapes, which inherently aligns more closely with human vision.
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness. To reveal model weaknesses, adversarial attacks are specifically optimized to generate small, barely perceivable image perturbations that flip the model prediction. Robustness against attacks can be gained by using adversarial examples during training, which in most cases reduces the measurable model attackability. Unfortunately, this technique can lead to robust overfitting, which results in non-robust models. In this paper, we analyze adversarially trained, robust models in the context of a specific network operation, the downsampling layer, and provide evidence that robust models have learned to downsample more accurately and suffer significantly less from downsampling artifacts, aka. aliasing, than baseline models. In the case of robust overfitting, we observe a strong increase in aliasing and propose a novel early stopping approach based on the measurement of aliasing.