English(EN) Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging

新方法确保AI排行榜的完整性，抵御自适应操纵

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员开发了一种名为“认证腐败预算”的新方法，以确保AI模型排行榜的完整性。该技术提供了任何时候都有效的排名声明，即使攻击者试图通过投票操纵或选择性披露私人模型变体等方法来操纵结果。认证腐败预算在记录达到一定数量后计算得出，保证声明的正确性或大量记录被损坏，能够抵御能够观察认证过程的自适应攻击者。 AI

影响增强了对AI模型评估的信任，这对于开发和部署决策至关重要。

排序理由该集群包含一篇详细介绍AI模型评估新方法的学术论文。[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 →

本文如何被排名

Signal score: 20 / 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模型评估新方法的学术论文。[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]

arXiv cs.AI TIER_1 English(EN) · Hamed Khosravi, Xiaoming Huo · 2026-10-09 04:00

认证腐败预算：自适应操纵下的随时有效排行榜声明

arXiv:2610.10597v1 Announce Type: cross Abstract: Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, selective disclosure of private variants, and benchmark contamination can each move a ranking. Existing guarant…

本文如何被排名

报道来源 [1]

认证腐败预算：自适应操纵下的随时有效排行榜声明

相关实体

相关话题