按年被提到
20152016 · 1 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1511.04599 · cs.LG

DeepFool: a simple and accurate method to fool deep neural networks

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-10-30 · 最近 2021-12-22
2不同的人
2活跃月份
2讨论串
114被引(OpenAlex)
arXiv 摘要(候选层不写导读)

State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the importance of this phenomenon, no effective methods have been proposed to accurately compute the robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets. In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show that our approach outperforms recent methods in the task of computing adversarial perturbations and making classifiers more robust.

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joshuawarner32 · 2016-10

“See also: https://arxiv.org/abs/1511.04599 IMO, (at least) two pieces of research on the subject means that the short answer really is "yes". Maybe not the exact technique used in the paper in the original post, but conceptually similar techniques.”

Universal adversarial perturbations原评论 ↗
评论orange3xchicken · 2021-12

“I'm less familiar with poisoning, but at least for test-time robustness, the current benchmark for image classifiers is AutoAttack [0,1]. It's an ensemble of adaptive & parameter-free gradient-based white-box and gradient-free black-box attacks. Submitted academic work is typically considered incomplete without an evaluation on AA (and sometimes deepfool …”

DARPA open sources resources to aid evaluation of adversarial AI defenses原评论 ↗