"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs

Abstract: LLMs have become increasingly powerful, with multilingual and multimodal capabilities improving by the day. These models are being evaluated through audits, alignment studies and red-teaming efforts to expose model vulnerabilities towards generating harmful, biased and unfair content. Existing red-teaming efforts have previously focused on the English language, using fixed template-based attacks; thus, models continue to be susceptible to multilingual jailbreaking strategies, especially in the multimodal context. In this study, we introduce a novel strategy that leverages code-mixing and phonetic perturbations to jailbreak LLMs for both text and image generation tasks. We also introduce two new jailbreak strategies that show higher effectiveness than baseline strategies. Our work presents a method to effectively bypass safety filters in LLMs while maintaining interpretability by applying phonetic misspellings to sensitive words in code-mixed prompts. Our novel prompts achieve a 99% Attack Success Rate for text generation and 78% for image generation, with Attack Relevance Rate of 100% for text generation and 95% for image generation when using the phonetically perturbed code-mixed prompts. Our interpretability experiments reveal that phonetic perturbations impact word tokenization, leading to jailbreak success. Our study motivates increasing the focus towards more generalizable safety alignment for multilingual multimodal models, especially in real-world settings wherein prompts can have misspelt words.