Authors

* External authors

Venue

Date

Share

Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Zhiyuan Zhang*

Lingjuan Lyu

Xingjun Ma*

Chenguang Wang*

Xu Sun*

* External authors

EMNLP 2022

2022

Abstract

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned samples. Although the clean weights of PLMs are readily available, existing methods have ignored this information in defending NLP models against backdoor attacks. In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models. Specifically, we leverage the clean pre-trained weights via two complementary techniques: (1) a two-step Fine-mixing technique, which first mixes the backdoored weights (fine-tuned on poisoned data) with the pre-trained weights, then fine-tunes the mixed weights on a small subset of clean data; (2) an Embedding Purification (E-PUR) technique, which mitigates potential backdoors existing in the word embeddings. We compare Fine-mixing with typical backdoor mitigation methods on three single-sentence sentiment classification tasks and two sentence-pair classification tasks and show that it outperforms the baselines by a considerable margin in all scenarios. We also show that our E-PUR method can benefit existing mitigation methods. Our work establishes a simple but strong baseline defense for secure fine-tuned NLP models against backdoor attacks.

Related Publications

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

NeurIPS, 2023
Xiaoxiao Sun*, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu, Hongdong Li*, Liang Zheng*

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally indicate more privacy leakage. Image…

UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition

NeurIPS, 2023
Yuyuan Li*, Chaochao Chen*, Yizhao Zhang*, Weiming Liu*, Lingjuan Lyu, Xiaolin Zheng*, Dan Meng*, Jun Wang*

With growing concerns regarding privacy in machine learning models, regulations have committed to granting individuals the right to be forgotten while mandating companies to develop non-discriminatory machine learning systems, thereby fueling the study of the machine unlearn…

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

NeurIPS, 2023
Jiaqi Wang*, Xingyi Yang*, Suhan Cui*, Liwei Che*, Lingjuan Lyu, Dongkuan Xu*, Fenglong Ma*

This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneo…

  • HOME
  • Publications
  • Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.