Authors

* External authors

Venue

Date

Share

Defending Against Backdoor Attacks in Natural Language Generation

Xiaofei Sun*

Xiaoya Li*

Yuxian Meng*

Xiang Ao*

Lingjuan Lyu

Jiwei Li*

Tianwei Zhang*

* External authors

AAAI 2023

2023

Abstract

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has been invested to how backdoor attacks can affect current NLG models and how to defend against these attacks. In this work, by giving a formal definition of backdoor attack and defense, we investigate this problem on two important NLG tasks, machine translation and dialog generation. Tailored to the inherent nature of NLG models (e.g., producing a sequence of coherent words given contexts), we design defending strategies against attacks.
We find that testing the backward probability of generating sources given targets yields effective defense performance against all different types of attacks, and is able to handle the {\it one-to-many} issue in many NLG tasks such as dialog generation. We hope that this work can raise the awareness of backdoor risks concealed in deep NLG systems and inspire more future work (both attack and defense) towards this direction.

Related Publications

FedMef: Towards Memory-efficient Federated Dynamic Pruning

CVPR, 2024
Hong Huang, Weiming Zhuang, Chen Chen, Lingjuan Lyu

Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources for training deep learning models. Neural netw…

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models

ICLR, 2024
Zhenting Wang, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas*, Shiqing Ma*

Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. One example is when a model trainer collects a set of im…

FedWon: Triumphing Multi-domain Federated Learning Without Normalization

ICLR, 2024
Weiming Zhuang, Lingjuan Lyu

Federated learning (FL) enhances data privacy with collaborative in-situ training on decentralized clients. Nevertheless, FL encounters challenges due to non-independent and identically distributed (non-i.i.d) data, leading to potential performance degradation and hindered c…

  • HOME
  • Publications
  • Defending Against Backdoor Attacks in Natural Language Generation

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.