这篇论文还原了AI宣传的生成流程，从50个网站翻出提示词指令，还发现背后用了Llama 3和Mistral模型。
论文发布名为 PROPAGIA 的法语宣传语料库，包含 2,646 篇文章，来自 2025 年 VIGINUM 和 INSIKT GROUP 披露的 Storm-1516/CopyCop 活动。与同期人类写作的主流媒体语料 SIPA 相比，PROPAGIA 在模糊性、主观性和负面性上显著更高，引用来源更少。分析发现 84 个 PROPAGIA 网站中有 50 个存在提示词指令泄漏，其中包括一份逐字的十点编辑规范。基于改写检测的分析支持 INSIKT GROUP 将活动归因于 Llama 3 系列模型，但也暗示 Mistral 系列模型的参与。
Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign
We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign. We introduce PROPAGIA, a corpus of 2,646 propagandist French articles from the Storm-1516/CopyCop campaign disclosed by VIGINUM and INSIKT GROUP in 2025. For comparison, we rely on SIPA, a corpus of human-written French mainstream press from the same period. Using topic modeling, vagueness and sentiment analysis, we first isolate persuasion techniques characteristic of propaganda, with PROPAGIA far exceeding SIPA in vagueness, subjectivity and negativity, and citing fewer sources. We then find prompt instruction leaks on 50 of the 84 PROPAGIA websites, including a verbatim ten-point editorial specification accounting for several of these differences, together with high cross-article redundancy. Finally, we show that rewriting-based detection supports INSIKT GROUP's attribution to the Llama 3 family, but also suggests the involvement of Mistral-family models.