English(EN) CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

新的CPInj攻击暴露了去中心化LLM提示优化中的漏洞

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-22 04:00

研究人员发现了一种名为CPInj的新型去中心化大型语言模型提示优化系统漏洞。该攻击针对协作式提示优化循环，恶意指令可以通过提示聚合注入并传播，从而降低性能并逃避当前防御。为解决此问题，提出了一种名为APAgg的面向防御的聚合方法，旨在净化恶意指令并部分恢复效用，尽管该攻击仍然是一个重大挑战。 AI

影响突出了去中心化LLM训练方法中的关键漏洞，需要为协作式提示优化提供更强大的安全措施。

排序理由详细介绍LLM提示优化新攻击和防御的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM提示优化新攻击和防御的学术论文。[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: 50 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad, David B. Emerson, Ruinan Jin, Deval Pandya, Xiaoxiao Li · 2026-07-22 04:00

CPInj：揭示文本协作式提示优化中的提示注入风险

arXiv:2607.18622v1 Announce Type: cross Abstract: Textual Collaborative Prompt Optimization (TCPO) extends Textgrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for large language models (LLMs) while keeping their d…