ProTransformer: Robustify Transformers via Plug-and-Play Paradigm

Zhichao Hou, Weizhi Gao, Yuchen Shen, Feiyi Wang, Xiaorui Liu

Keywords: Transformers, Adversarial Robustness, Large Language Models

Abstract: Transformer-based architectures have dominated various areas of machine learning in recent years. In this paper, we introduce a novel robust attention mechanism designed to enhance the resilience of transformer-based architectures. Crucially, this technique can be integrated into existing transformers as a plug-and-play layer, improving their robustness without the need for additional training or fine-tuning. Through comprehensive experiments and ablation studies, we demonstrate that our ProTransformer significantly enhances the robustness of transformer models across a variety of prediction tasks, attack mechanisms, backbone architectures, and data domains. Notably, without further fine-tuning, the ProTransformer consistently improves the performance of vanilla transformers by 19.5\%, 28.3\%, 16.1\%, and 11.4\% for BERT, ALBERT, DistilBERT, and RoBERTa, respectively, under the classical TextFooler attack. Furthermore, ProTransformer shows promising resilience in large language models (LLMs) against prompting-based attacks, improving the performance of T5 and LLaMA by 24.8\% and 17.8\%, respectively, and enhancing Vicuna by an average of 10.4\% against the Jailbreaking attack. Beyond the language domain, ProTransformer also demonstrates outstanding robustness in both vision and graph domains.

Primary Area: Safety in machine learning

Submission Number: 20720