# DBIA: Data-free Backdoor Injection Attack against Transformer Networks

Source: [DBIA: Data-free Backdoor Injection Attack against Transformer Networks](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d86b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:50.786Z

Authors: Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang

Published: 2021-11-22T08:13:51.000Z

## Abstract

Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds triggers in the model and controls the model behavior when the triggers are presented, little is known whether such an attack is still valid on the transformer models and if so, whether it can be done in a more cost-efficient manner. In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inherent attention mechanism of transformers to generate triggers and injecting the backdoor using the poisoned surrogate dataset. We conducted extensive experiments based on three benchmark transformers, i.e., ViT, DeiT and Swin Transformer, on two mainstream image classification tasks, i.e., CIFAR10 and ImageNet. The evaluation results demonstrate that, consuming fewer resources, our approach can embed backdoors with a high success rate and a low impact on the performance of the victim transformers. Our code is available at https://anonymous.4open.science/r/DBIA-825D.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Recognition on ImageNet 1K (val)](<https://www.sota2.com/research/sota/image-recognition-on-imagenet-1k-val.md>): Image Recognition; ImageNet-1k (val); CDA: 79.47.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.11870>)

[PDF](<https://arxiv.org/pdf/2111.11870.pdf>)