@inproceedings{song-etal-2020-adversarial,
    title = "Adversarial Semantic Collisions",
    author = "Song, Congzheng  and
      Rush, Alexander  and
      Shmatikov, Vitaly",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.emnlp-main.344/",
    doi = "10.18653/v1/2020.emnlp-main.344",
    pages = "4198--4210",
    abstract = "We study \textit{semantic collisions}: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks which rely on analyzing the meaning and similarity of texts{---}including paraphrase identification, document retrieval, response suggestion, and extractive summarization{---}are vulnerable to semantic collisions. For example, given a target query, inserting a crafted collision into an irrelevant document can shift its retrieval rank from 1000 to top 3. We show how to generate semantic collisions that evade perplexity-based filtering and discuss other potential mitigations. Our code is available at \url{https://github.com/csong27/collision-bert}."
}