@inproceedings{verma-etal-2025-multiguard,
    title = "{MULTIGUARD}: An Efficient Approach for {AI} Safety Moderation Across Languages and Modalities",
    author = "Verma, Sahil  and
      Hines, Keegan  and
      Bilmes, Jeff  and
      Siska, Charlotte  and
      Zettlemoyer, Luke  and
      Gonen, Hila  and
      Singh, Chandan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.819/",
    pages = "16184--16198",
    ISBN = "979-8-89176-332-6",
    abstract = "The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current detection approaches are fallible, and are particularly susceptible to attacks that exploit mismatched generalization of model capabilities (e.g., prompts in low-resource languages or prompts provided in non-text modalities such as image and audio). To tackle this challenge, we propose OMNIGUARD, an approach for detecting harmful prompts across languages and modalities. Our approach (i) identifies internal representations of an LLM/MLLM that are aligned across languages or modalities and then (ii) uses them to build a language-agnostic or modality-agnostic classifier for detecting harmful prompts. OMNIGUARD improves harmful prompt classification accuracy by 11.57{\%} over the strongest baseline in a multilingual setting, by 20.44{\%} for image-based prompts, and sets a new SOTA for audio-based prompts. By repurposing embeddings computed during generation, OMNIGUARD is also very efficient ({\ensuremath{\approx}} 120{\texttimes} faster than the next fastest baseline). Code and data are available at https://github.com/vsahil/OmniGuard"
}