English(EN) CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

新框架可实现对AI生成代码的定向投毒

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了一个名为CodePoisonRAG的新框架，该框架可以向检索增强代码生成（RACG）系统生成的代码中注入特定的漏洞。该框架通过将良性代码转换为有毒的伪造品来工作，即使攻击者无法访问受害者的内部系统，这些伪造品也能与攻击者选择的弱点相符。这些有毒的伪造品被设计成在语义上被错误标记，看起来是安全的，但实际上包含漏洞。实验表明，在不同代码生成模型甚至针对CodeGuarder等安全系统传播这些定向弱点方面，成功率很高。 AI

影响突出了AI代码生成的一个新攻击向量，可能影响使用这些工具开发的软件的安全性。

排序理由学术论文，详细介绍了针对AI代码生成的新攻击框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了针对AI代码生成的新攻击框架。[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: safety, paper, product; 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.LG TIER_1 English(EN) · Varun Gadey, Ziad Marey, Alexandra Dmitrienko · 2026-09-03 04:00

CodePoisonRAG：检索增强代码生成的知识投毒攻击

arXiv:2609.02774v1 Announce Type: cross Abstract: Retrieval-Augmented Code Generation (RACG) improves LLM-based software development by retrieving external code artifacts, documentation, and patches, and incorporating them into the generation context. This reliance on external kn…

本文如何被排名

报道来源 [1]

CodePoisonRAG：检索增强代码生成的知识投毒攻击

相关实体

相关话题