Nature, Published online: 10 March 2026; doi:10.1038/d41586-026-00778-4
The paper demonstrated 90% success against knowledge bases containing millions of documents, using gradient-optimized payloads. What I tested is a vocabulary-engineering approach — no optimization against the embedding model — against a 5-document corpus. The corpus is obviously smaller than what the paper evaluated, so the success rate isn’t directly comparable. The value of a small local lab is reproducibility and clarity of mechanism, not scale. In a real production knowledge base with hundreds of documents on the same topic, the attacker needs more poisoned documents to reliably dominate the top-k — but the attack remains viable. The PoisonedRAG authors showed that even at millions-of-documents scale, five crafted documents are sufficient when using their optimization approach.
。Snipaste - 截图 + 贴图对此有专业解读
12:25, 13 марта 2026Культура
vertices ← ,[⍳4] faces(+⍤2) v_cnt(⌿⍤2),[2.5] 3 0 1 2⍉l⊤⊢l⍴⍳×/l
，更多细节参见谷歌
I tested Xiaomi's matte-glass tablet for a month, and it effectively replaced my iPad。yandex 在线看是该领域的重要参考
让我们深入分析，回溯宗教教派的神学分歧 （什叶派 vs 逊尼派）、 帝国地缘的博弈 （萨法维 vs 奥斯曼）以及种族认同的纠葛（波斯 vs 阿拉伯）三大维度，解析这场跨越千年的文明冲突，究竟是如何引爆了今天的波斯湾危机。