English(EN) Rethinking Indirect Prompt Injection as a Test-Time Search Problem

新研究将AI提示注入视为测试时搜索问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

一篇新的研究论文提出将间接提示注入攻击重新构想为测试时搜索问题。作者引入了一个代理攻击者，旨在探索系统的攻击面、推理策略并根据反馈进行调整。他们的研究结果表明，增加攻击者的计算资源可以增强漏洞的发现和利用，这凸显了在评估使用工具的代理的安全时，考虑攻击者的搜索过程和计算预算的重要性。 AI

影响这项研究可以通过关注自适应搜索策略，从而导致对AI代理进行更鲁棒的安全评估。

排序理由该集群包含一篇关于AI安全新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇关于AI安全新方法的学术论文。[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。

arXiv cs.AI TIER_1 English(EN) · Duong M. Nguyen, Joon Sik Kim, Blazej Manczak, Vaikkunth Mugunthan · 2026-09-07 04:00

将间接提示注入视为测试时搜索问题

arXiv:2609.04495v1 Announce Type: new Abstract: We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this formulation, we introduce an agentic attacker with a…