Yan Solihin — accepted AI-conference papers

2025

Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations

Mansour Al Ghanim, Jiaqi Xue, Rochana Prih Hastuti, Mengxin Zheng, Yan Solihin, Qian Lou

EMNLP 2025

We present a study to benchmark representative watermarking methods in cross-lingual settings. The current literature mainly focuses on the evaluation of watermarking methods for the English language. However, the literature for evaluating watermarking in cross-lingual settings is scarce. This resul

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Jailbreaking LLMs with Arabic Transliteration and Arabizi

Mansour Al Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, Qian Lou

EMNLP 2024main

This study identifies the potential vulnerabilities of Large Language Models (LLMs) to ‘jailbreak’ attacks, specifically focusing on the Arabic language and its various forms. While most research has concentrated on English-based prompt manipulation, our investigation broadens the scope to investiga…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗