“Yes, I agree with you. (No idea who downvoted my and why either.) This (well known) illusion is NOT an adversarial example. Though, I explain why for people working with AI (e.g. me) the title seemed like mentioning an adversarial example. There are plenty of examples of "just rotate and a vulture becomes an orangutan" where it does not look like an oran…”
Exploring the Landscape of Spatial Robustness
The study of adversarial robustness has so far largely focused on perturbations bound in p-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and rotations. In this work, we thoroughly investigate the vulnerability of neural network--based classifiers to rotations and translations. While data augmentation offers relatively small robustness, we use ideas from robust optimization and test-time input aggregation to significantly improve robustness. Finally we find that, in contrast to the p-norm case, first-order methods cannot reliably find worst-case perturbations. This highlights spatial robustness as a fundamentally different setting requiring additional study. Code available at https://github.com/MadryLab/adversarial_spatial and https://github.com/MadryLab/spatial-pytorch.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“The part about AI being very sensitive to small perturbations of their input is actually a very active research topic (and coincidentally the subject of my PhD). Most vision AIs suffer from poor spatial robustness [1], you can drastically lower their accuracy simply by translating the inputs by well-chosen (adversarial) translations of a few pixels! I don…”