Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shahriar, Sadat, Ayoobi, Navid, Mukherjee, Arjun, Musharrat, Mostafa, Vamsi, Sai Vishnu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915655937163264
author Shahriar, Sadat
Ayoobi, Navid
Mukherjee, Arjun
Musharrat, Mostafa
Vamsi, Sai Vishnu
author_facet Shahriar, Sadat
Ayoobi, Navid
Mukherjee, Arjun
Musharrat, Mostafa
Vamsi, Sai Vishnu
contents The local news landscape, a vital source of reliable information for 28 million Americans, faces a growing threat from Pink Slime Journalism, a low-quality, auto-generated articles that mimic legitimate local reporting. Detecting these deceptive articles requires a fine-grained analysis of their linguistic, stylistic, and lexical characteristics. In this work, we conduct a comprehensive study to uncover the distinguishing patterns of Pink Slime content and propose detection strategies based on these insights. Beyond traditional generation methods, we highlight a new adversarial vector: modifications through large language models (LLMs). Our findings reveal that even consumer-accessible LLMs can significantly undermine existing detection systems, reducing their performance by up to 40% in F1-score. To counter this threat, we introduce a robust learning framework specifically designed to resist LLM-based adversarial attacks and adapt to the evolving landscape of automated pink slime journalism, and showed and improvement by up to 27%.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05331
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats
Shahriar, Sadat
Ayoobi, Navid
Mukherjee, Arjun
Musharrat, Mostafa
Vamsi, Sai Vishnu
Computation and Language
Machine Learning
The local news landscape, a vital source of reliable information for 28 million Americans, faces a growing threat from Pink Slime Journalism, a low-quality, auto-generated articles that mimic legitimate local reporting. Detecting these deceptive articles requires a fine-grained analysis of their linguistic, stylistic, and lexical characteristics. In this work, we conduct a comprehensive study to uncover the distinguishing patterns of Pink Slime content and propose detection strategies based on these insights. Beyond traditional generation methods, we highlight a new adversarial vector: modifications through large language models (LLMs). Our findings reveal that even consumer-accessible LLMs can significantly undermine existing detection systems, reducing their performance by up to 40% in F1-score. To counter this threat, we introduce a robust learning framework specifically designed to resist LLM-based adversarial attacks and adapt to the evolving landscape of automated pink slime journalism, and showed and improvement by up to 27%.
title Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2512.05331