Empirical tests across six LLMs show systematic prompt injection vulnerabilities, with higher malicious compliance in non-English languages and complex obfuscated prompts.
Perspective chapter: Ransomware,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios
Empirical tests across six LLMs show systematic prompt injection vulnerabilities, with higher malicious compliance in non-English languages and complex obfuscated prompts.