# Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign

arXiv: https://arxiv.org/abs/2608.15746 · HTML: https://mlsanity.com/paper/2608.15746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://mlsanity.com/paper/2009.02696/) (2020)
- [Predicting Factuality of Reporting and Bias of News Media Sources](https://mlsanity.com/paper/1810.01765/) (2018)
- [A Survey on Computational Propaganda Detection](https://mlsanity.com/paper/2007.08024/) (2020)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [Raidar: geneRative AI Detection viA Rewriting](https://mlsanity.com/paper/2401.12970/) (2024)
- [Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websites](https://mlsanity.com/paper/2305.09820/) (2023)
- [Findings of the NLP4IF-2019 Shared Task on Fine-Grained Propaganda Detection](https://mlsanity.com/paper/1910.09982/) (2019)
- [Interpretable Propaganda Detection in News Articles](https://mlsanity.com/paper/2108.12802/) (2021)
- [Measuring vagueness and subjectivity in texts: from symbolic to neural VAGO](https://mlsanity.com/paper/2309.06132/) (2023)
- [Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification](https://mlsanity.com/paper/2402.03780/) (2024)
- [Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification](https://mlsanity.com/paper/2604.01936/) (2026)

## Abstract (arXiv)

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.