GraphRAG-Based NLP at Risk: Graphemic Dot-Level Adversarial Attack on Arabic Sentiment and LLM Retrieval-Augmented Models

Abdullah Melhem, Ahmed AlEroud, Craig Douglas Albert. GraphRAG-Based NLP at Risk: Graphemic Dot-Level Adversarial Attack on Arabic Sentiment and LLM Retrieval-Augmented Models. In Aijun An, Alfredo Cuzzocrea, Hongxin Hu, editors, Social Networks Analysis and Mining - 17th International Conference, ASONAM 2025, Niagara Falls, ON, Canada, August 25-28, 2025, Proceedings, Part I. Volume 16322 of Lecture Notes in Computer Science, pages 252-263, Springer, 2025. [doi]

@inproceedings{MelhemAA25,
  title = {GraphRAG-Based NLP at Risk: Graphemic Dot-Level Adversarial Attack on Arabic Sentiment and LLM Retrieval-Augmented Models},
  author = {Abdullah Melhem and Ahmed AlEroud and Craig Douglas Albert},
  year = {2025},
  doi = {10.1007/978-3-032-13513-1_21},
  url = {https://doi.org/10.1007/978-3-032-13513-1_21},
  researchr = {https://researchr.org/publication/MelhemAA25},
  cites = {0},
  citedby = {0},
  pages = {252-263},
  booktitle = {Social Networks Analysis and Mining - 17th International Conference, ASONAM 2025, Niagara Falls, ON, Canada, August 25-28, 2025, Proceedings, Part I},
  editor = {Aijun An and Alfredo Cuzzocrea and Hongxin Hu},
  volume = {16322},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-032-13513-1},
}