@inproceedings{asl-etal-2023-robustembed,
    title = "{R}obust{E}mbed: Robust Sentence Embeddings Using Self-Supervised Contrastive Pre-Training",
    author = "Asl, Javad  and
      Blanco, Eduardo  and
      Takabi, Daniel",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-emnlp.305/",
    doi = "10.18653/v1/2023.findings-emnlp.305",
    pages = "4587--4603",
    abstract = "Pre-trained language models (PLMs) have demonstrated their exceptional performance across a wide range of natural language processing tasks. The utilization of PLM-based sentence embeddings enables the generation of contextual representations that capture rich semantic information. However, despite their success with unseen samples, current PLM-based representations suffer from poor robustness in adversarial scenarios. In this paper, we propose RobustEmbed, a self-supervised sentence embedding framework that enhances both generalization and robustness in various text representation tasks and against diverse adversarial attacks. By generating high-risk adversarial perturbations to promote higher invariance in the embedding space and leveraging the perturbation within a novel contrastive objective approach, RobustEmbed effectively learns high-quality sentence embeddings. Our extensive experiments validate the superiority of RobustEmbed over previous state-of-the-art self-supervised representations in adversarial settings, while also showcasing relative improvements in seven semantic textual similarity (STS) tasks and six transfer tasks. Specifically, our framework achieves a significant reduction in attack success rate from 75.51{\%} to 39.62{\%} for the BERTAttack attack technique, along with enhancements of 1.20{\%} and 0.40{\%} in STS tasks and transfer tasks, respectively."
}