PulseAugur
实时 08:27:49
English(EN) Trust Under Siege: Label Spoofing Attacks against Machine Learning for Android Malware Detection

新研究揭示了针对机器学习恶意软件检测的标签欺骗攻击

一项新的研究论文介绍了一种名为“标签欺骗攻击”的新型威胁,攻击者会巧妙地将恶意模式嵌入到良性软件中。这些模式会欺骗杀毒引擎将合法文件误分类为有害文件,从而污染用于训练机器学习恶意软件检测器的训练数据集。该研究通过AndroVenom展示了这一点,该方法仅用1%的被污染样本就能对最先进的机器学习模型造成拒绝服务攻击,并通过最小的数据修改来改变特定的良性样本决策。研究结果引起了人们对依赖杀毒软件注释的机器学习训练过程的可靠性的严重担忧。 AI

影响 凸显了机器学习训练数据完整性的漏洞,可能影响人工智能驱动的安全系统的可靠性。

排序理由 详细介绍针对机器学习系统的新型攻击向量的研究论文。[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 →

新研究揭示了针对机器学习恶意软件检测的标签欺骗攻击

本文如何被排名

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍针对机器学习系统的新型攻击向量的研究论文。[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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Tianwei Lan, Luca Demetrio, Farid Nait-Abdesselam, Yufei Han, Simone Aonzo ·

    信任受损:针对机器学习安卓恶意软件检测的标签欺骗攻击

    arXiv:2503.11841v2 Announce Type: replace-cross Abstract: Machine Learning (ML) malware detectors rely heavily on crowd-sourced AntiVirus (AV) labels, with platforms like VirusTotal serving as trusted sources of malware annotations. But what if attackers could manipulate these la…