Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang


Abstract
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models and their limited access make improving their robustness a challenging task. Among various defense strategies, randomized smoothing has shown great potential for LLMs, as it does not require full access to the model’s parameters or fine-tuning via adversarial training. However, randomized smoothing involves adding noise to the input before model prediction, and the final model’s robustness largely depends on the model’s performance on these noise-corrupted data. Its effectiveness is often limited by the model’s sub-optimal performance on noisy data. To address this issue, we propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. We call this procedure self-denoised smoothing. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility. Our experimental results indicate that our method surpasses existing methods in both empirical and certified robustness in defending against adversarial attacks for both downstream tasks and human alignments (i.e., jailbreak attacks). Our code is publicly available at https://github.com/UCSB-NLP-Chang/SelfDenoise.
Anthology ID:
2024.naacl-short.23
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
246–257
Language:
URL:
https://aclanthology.org/2024.naacl-short.23
DOI:
Bibkey:
Cite (ACL):
Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, and Shiyu Chang. 2024. Advancing the Robustness of Large Language Models through Self-Denoised Smoothing. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 246–257, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing (Ji et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2024.naacl-short.23.pdf
Copyright:
 2024.naacl-short.23.copyright.pdf