按年被提到
20122012 · 3 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1206.6389 · cs.LG

Poisoning Attacks against Support Vector Machines

Battista Biggio, Blaine Nelson, Pavel Laskov · 2012
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2012-07-23 · 最近 2012-12-03
3不同的人
2活跃月份
3讨论串
1,128被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We investigate a family of poisoning attacks against Support Vector Machines (SVM). Such attacks inject specially crafted training data that increases the SVM's test error. Central to the motivation for these attacks is the fact that most learning algorithms assume that their training data comes from a natural or well-behaved distribution. However, this assumption does not generally hold in security-sensitive settings. As we demonstrate, an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data. The proposed attack uses a gradient ascent strategy in which the gradient is computed based on properties of the SVM's optimal solution. This method can be kernelized and enables the attack to be constructed in the input space even for non-linear kernels. We experimentally demonstrate that our gradient ascent procedure reliably identifies good local maxima of the non-convex validation error surface, which significantly increases the classifier's test error.

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 3 次