English(EN) Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

对监督学习模型进行数据投毒攻击评估

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

一篇新发表在arXiv上的研究论文评估了两种数据投毒攻击——标签翻转和后门投毒——在常见监督学习模型上的有效性。研究发现，标签翻转显著降低了逻辑回归和线性SVM模型的性能，而随机森林则保持更稳定。然而，后门投毒被证明非常有效，在所有测试的模型和数据集上实现了近乎完美的攻击成功率，同时保持了高清洁测试准确率，凸显了此类定向攻击的隐蔽性。 AI

影响强调了后门投毒攻击的隐蔽性和有效性，突显了对AI模型进行超越标准指标的高级安全评估的必要性。

排序理由该集群包含一篇详细介绍监督学习模型数据投毒攻击实证评估的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍监督学习模型数据投毒攻击实证评估的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Toshif Khan (Minot State University), Muhammad Abusaqer (Minot State University) · 2026-09-11 04:00

监督学习中数据投毒攻击的实证评估

arXiv:2609.10952v1 Announce Type: cross Abstract: Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST wi…

本文如何被排名

报道来源 [1]

监督学习中数据投毒攻击的实证评估

相关实体

相关话题