@inproceedings{gainski-balazy-2023-step,
    title = "Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks",
    author = "Gai{\'n}ski, Piotr  and
      Ba{\l}azy, Klaudia",
    editor = "Vlachos, Andreas  and
      Augenstein, Isabelle",
    booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.eacl-main.149/",
    doi = "10.18653/v1/2023.eacl-main.149",
    pages = "2038--2048",
    abstract = "We propose a novel gradient-based attack against transformer-based language models that searches for an adversarial example in a continuous space of tokens probabilities. Our algorithm mitigates the gap between adversarial loss for continuous and discrete text representations by performing multi-step quantization in a quantization-compensation loop. Experiments show that our method significantly outperforms other approaches on various natural language processing (NLP) tasks."
}