Universal Adversarial Robustness of Texture and Shape-Biased Models
| Autor: | Emil Lupu, Ben Glocker, Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Adversarial system Robustness (computer science) Computer science Texture (cosmology) Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Deep neural networks Noise (video) Algorithm cs.CV ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | IEEE International Conference on Image Processing (ICIP) |
| DOI: | 10.48550/arxiv.1911.10364 |
| Popis: | Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial Perturbations (UAPs). We use UAPs to evaluate the robustness of DNN models with varying degrees of shape-based training. We find that shape-biased models do not markedly improve adversarial robustness, and we show that ensembles of texture and shape-biased models can improve universal adversarial robustness while maintaining strong performance. Comment: In Proceedings of the 28th IEEE International Conference on Image Processing (ICIP 2021), code available at: https://github.com/kenny-co/sgd-uap-torch |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|