PulseAugur
中
实时 17:44:29
English(EN) Backdoored Agents Pass All Scans: VIDRAFT's ViKernel Blocks 290/290 `curl|bash` Payloads at Execution Time

研究人员演示了LLM后门能够逃避微调;ViKernel提供执行时防御

Hu等人的一篇新论文详细介绍了预训练数据的一小部分如何能在LLM代理中嵌入持久的远程代码执行后门,该后门能够逃避标准的微调和行为扫描。VIDRAFT的FINAL-Bench团队在Qwen3架构模型上复制了此后门,并证明了其ViKernel系统通过在执行时强制执行允许操作的白名单,成功阻止了所有恶意载荷。该研究强调,防御此类后门需要判断操作,而不是试图枚举未知的触发器。 AI

影响 强调了一类新的LLM漏洞和一种潜在的防御策略,影响AI安全和代理开发。

排序理由 研究论文,详细介绍了新颖的LLM安全漏洞和提出的防御机制。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

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

研究人员演示了LLM后门能够逃避微调;ViKernel提供执行时防御

本文如何被排名

Signal score
5 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文,详细介绍了新颖的LLM安全漏洞和提出的防御机制。[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
safety, paper, model release
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]

  1. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    后门代理程序通过所有扫描:VIDRAFT的ViKernel在执行时阻止了290/290个`curl|bash`载荷

    <h1> Backdoored Agents Pass All Scans: VIDRAFT's ViKernel Blocks 290/290 <code>curl|bash</code> Payloads at Execution Time </h1> <blockquote> <p><strong>TL;DR:</strong> A new paper (Hu et al., arXiv:2610.37741) demonstrates that poisoning just 0.1% of pretraining data can embed a…