paperJune 2026Unreviewed

An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios

Caglar Uysal, Baturay Birinci, Süha Orhun Mutluergil, Orçun Çetin

Abstract

Large Language Models (LLMs) have rapidly evolved, transforming industries by automating complex tasks and generating human-like content. However, as their adoption accelerates, prompt injection vulnerabilities have become increasingly apparent. Malicious actors exploit these weaknesses to generate phishing emails, deceptive websites, nd malware, posing serious security risks. This paper presents an empirical evaluation of six state-of-the-art LLMs (DeepSeek, GPT, Gemini, Grok, Llama, and Qwen)

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{uysal2026empirical,
  title = {{An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios}},
  author = {Caglar Uysal and Baturay Birinci and Süha Orhun Mutluergil and Orçun Çetin},
  year = {2026},
  month = jun,
  eprint = {2606.29602},
  archivePrefix = {arXiv},
  doi = {10.23919/EDCCCCPS00002.2026.00039},
  url = {https://arxiv.org/abs/2606.29602}
}