Exaggeration-based Fake Cybersecurity News Detection

Felemban A., GHALEB M. M. S., Felemban M.

1st ACM Workshop on Deepfake, Deception and Disinformation Security, 3D-Sec 2025, Taipei, Tayvan, 13 - 17 Ekim 2025, ss.1-4, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1145/3733813.3764365
  • Basıldığı Şehir: Taipei
  • Basıldığı Ülke: Tayvan
  • Sayfa Sayıları: ss.1-4
  • Anahtar Kelimeler: Cybersecurity, Fake news, LLM, Misinformation detection
  • Kocaeli Üniversitesi Adresli: Evet

Özet

We address the challenge of detecting exaggeration in cybersecurity tweets on X, where misinformation spreads rapidly. Our novel framework uses local Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to gather evidence and assess tweets' rhetorical intensity, offering graded exaggeration scores. Validated through a human study and a pilot that matches LLM results with human labels, this work lays the groundwork for improved misinformation detection tools.