PulseAugur
实时 06:41:43

新的Groundhog Bit-Flip攻击利用MoE LLM,导致大规模输出膨胀

研究人员开发了一种名为Groundhog Bit-Flip Attack (GBFA)的新攻击方法,该方法针对混合专家(MoE)大型语言模型。该攻击利用了MoE架构中的路由机制,其中特定专家可以与特定token相关联。通过操纵路由层比特,GBFA可以导致模型输出长度显著膨胀,在对话、推理和代理任务中,解码token使用量平均增加了5912%。该攻击仅需禁用少量专家即可实现,凸显了MoE设计中的鲁棒性漏洞。 AI

影响 揭示了MoE架构中的一个重大漏洞,可能影响大型语言模型的可靠性和安全性。

排序理由 研究论文,详细介绍了针对LLM的新攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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Groundhog Bit-Flip攻击利用MoE LLM,导致大规模输出膨胀

本文如何被排名

Signal score
28 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文,详细介绍了针对LLM的新攻击方法。[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.CL TIER_1 English(EN) · Huakang Lin, Tiancheng Zheng, Mingxuan Sun, Tianhong Xu, Fan Zhang, Yunsi Fei, Ruyi Ding ·

    土拨鼠比特翻转攻击:通过比特翻转在混合专家LLM中播下无限生成循环的种子

    arXiv:2608.25276v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However, this adaptive design introduces a new attack surfa…