按年被提到
20192019 · 1 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1906.04584 · cs.LG

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang, Huan Zhang, Ilya Razenshteyn, Sebastien Bubeck · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-06-13 · 最近 2021-08-06
2不同的人
2活跃月份
2讨论串
298被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ adversarial training to improve the performance of randomized smoothing. We design an adapted attack for smoothed classifiers, and we show how this attack can be used in an adversarial training setting to boost the provable robustness of smoothed classifiers. We demonstrate through extensive experimentation that our method consistently outperforms all existing provably $\ell_2$-robust classifiers by a significant margin on ImageNet and CIFAR-10, establishing the state-of-the-art for provable $\ell_2$-defenses. Moreover, we find that pre-training and semi-supervised learning boost adversarially trained smoothed classifiers even further. Our code and trained models are available at http://github.com/Hadisalman/smoothing-adversarial .

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orange3xchicken · 2021-08

“It turns out that a similar technique, where you basically apply noise multiple times to a single image, and average predictions over all noisy images- equivalent to convolving your nn with Gaussian noise yields near state of the art bounds on provable robustness (under a specific class of attacks). The issue is the magnitude of noise you need in order to…”

Fooling Neural Networks [pdf]原评论 ↗
被提交为 story · 1 次