@inproceedings{mamta-etal-2026-tinyattack,
    title = "{T}iny{A}ttack: Exploring Stylistic Vulnerabilities in Large Language Models",
    author = "Mamta, Mamta  and
      Grecu, Bogdan  and
      Cocarascu, Oana",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1987/",
    pages = "39933--39962",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have demonstrated impressive results in natural language processing (NLP) tasks, however, their brittleness against subtle input perturbations continues to pose a significant challenge. Existing research on robustness has predominantly focused on standard text-based perturbations and the use of invisible characters and homoglyphs, while overlooking the impact of stylized characters increasingly prevalent on social media. To address this, we propose $\texttt{TinyAttack}$, a novel adversarial attack framework designed to exploit vulnerabilities in LLMs through Unicode-based stylistic transformations. $\texttt{TinyAttack}$ utilises five Unicode variants to modify the visual rendering of text without altering its underlying semantic or syntactic structure. Our comprehensive evaluation on both open-source (Llama, Mistral, Gemma, Qwen) and closed-source LLMs (Gemini, GPT) demonstrates their susceptibility to these stylized inputs, with performance drops ranging from 29-92{\%} and 6-88.5{\%}, respectively, across all tasks.Our code is available at https://github.com/TRAI-group/TinyAttack."
}