PulseAugur
中
实时 08:57:35
English(EN) SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

新的SynGhost攻击利用具有隐形后门的预训练语言模型

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了SynGhost，这是一种利用预训练语言模型（PLMs）漏洞的新型后门攻击。该攻击将多个语法后门注入预训练数据中，使其能够在没有明确目标设置或易于识别的触发器的情况下转移到各种下游任务。SynGhost在保留PLM原始能力的同时，构成了重大威胁，并能规避困惑度过滤器和maxEntropy等常见防御措施。 AI

影响 这项研究突显了预训练语言模型的新漏洞，可能影响AI系统的安全性和可靠性。

排序理由 该集群包含一篇详细介绍AI模型新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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SynGhost攻击利用具有隐形后门的预训练语言模型

本文如何被排名

Signal score
15 / 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AI模型新攻击方法的学术论文。[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.AI TIER_1 English(EN) · Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu ·

    SynGhost：通过语法迁移实现不可见且通用的任务无关后门攻击

    arXiv:2402.18945v5 Announce Type: replace-cross Abstract: Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks…

相关话题