按年被提到
20172019 · 1 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1712.02779 · cs.LG

Exploring the Landscape of Spatial Robustness

Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-03-08 · 最近 2025-10-15
2不同的人
2活跃月份
2讨论串
300被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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
评论stared · 2019-03

“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…”

Is It a Duck or a Rabbit? For Google Cloud Vision, Depends on Image Rotation原评论 ↗
评论jeremyscanvic · 2025-10

“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…”

Beliefs that are true for regular software but false when applied to AI原评论 ↗