PulseAugur
中
实时 09:13:49
English(EN) Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse

新的DAR方法使用干净数据在模型中嵌入持久性后门

研究人员开发了一种名为DAR(Discover-and-Relabel)的新方法,即使在使用干净数据进行训练的情况下,也能在机器学习模型中嵌入持久性后门。与依赖人工触发器的传统后门攻击不同,DAR识别低维特征子空间中自然出现的模式,并使用仅标签的投毒。即使在知识蒸馏(一种常见的防御技术)之后,该方法仍然有效,在ImageNet分类和基于CLIP的提示调优上保持了超过96%的攻击成功率。 AI

影响 这项研究揭示了机器学习模型的一种新颖漏洞,可能影响AI系统的安全性和可信度。

排序理由 该集群包含一篇详细介绍机器学习模型后门攻击新方法的论文。[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 →

新的DAR方法使用干净数据在模型中嵌入持久性后门

本文如何被排名

Signal score
14 / 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机器学习模型后门攻击新方法的论文。[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) · Junhoo Lee, Baekseung Kim, Seungyeon Kim, Nojun Kwak ·

    干净的数据仍可能带有后门:支持持久性后门以供模型复用

    arXiv:2610.21208v1 Announce Type: cross Abstract: Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining normal behavior on clean samples. Since these artificial triggers are absent in c…