PulseAugur
中
实时 10:13:19
English(EN) A model you download is code you didn’t write, trained on data you never saw. In 2026, poisoning an open-weight model got cheap: ~10 examples, under £75, under

开放权重AI模型易受廉价后门攻击

一位安全研究人员演示了开放权重AI模型如何轻易地被恶意后门所污染。仅需花费不到75英镑和不到一小时的时间,大约10个样本就可以植入一个后门,该后门会在未见过的提示下触发。该研究人员开发了一个离线实验室环境来防御此类攻击。 AI

影响 凸显了开放权重AI模型部署中的重大安全风险,可能影响信任和采用。

排序理由 演示了开放权重AI模型的安全漏洞。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

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

开放权重AI模型易受廉价后门攻击

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
演示了开放权重AI模型的安全漏洞。[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, infra
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. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    你下载的模型是你未曾编写的代码,基于你从未见过的数据训练而成。2026年,毒化开源模型变得廉价:约10个样本,花费不到75英镑,低于

    A model you download is code you didn’t write, trained on data you never saw. In 2026, poisoning an open-weight model got cheap: ~10 examples, under £75, under an hour — and the backdoor fires on prompts it never trained on. So I built the defender’s lab. Every command runs offli…