English

Unitary Multi-Margin BERT for Robust Natural Language Processing

Computation and Language 2024-10-17 v1 Artificial Intelligence

Abstract

Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this paper reports a novel, universal technique that drastically improves the robustness of Bidirectional Encoder Representations from Transformers (BERT) by combining the unitary weights with the multi-margin loss. We discover that the marriage of these two simple ideas amplifies the protection against malicious interference. Our model, the unitary multi-margin BERT (UniBERT), boosts post-attack classification accuracies significantly by 5.3% to 73.8% while maintaining competitive pre-attack accuracies. Furthermore, the pre-attack and post-attack accuracy tradeoff can be adjusted via a single scalar parameter to best fit the design requirements for the target applications.

Keywords

Cite

@article{arxiv.2410.12759,
  title  = {Unitary Multi-Margin BERT for Robust Natural Language Processing},
  author = {Hao-Yuan Chang and Kang L. Wang},
  journal= {arXiv preprint arXiv:2410.12759},
  year   = {2024}
}
R2 v1 2026-06-28T19:24:32.199Z