# Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer

Source: [Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer](<https://www.sota2.com/research/paper/68fa76131e209131cea6b441>)

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

Data updated: 2025-10-26T03:46:34.345Z

Authors: Xueluan Gong, Bowei Tian, Meng Xue, Shuike Li, Yanjiao Chen, Qian Wang

Published: 2024-12-06T04:39:41.000Z

## Abstract

Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works focus on dirty-label attacks with wrongly-labeled poisoned training samples, which may fail if a benign model trainer corrects the labels. In this paper, we propose Megatron, an evasive clean-label backdoor attack against vision transformers, where the attacker injects the backdoor without manipulating the data-labeling process. To generate an effective trigger, we customize two loss terms based on the attention mechanism used in transformer networks, i.e., latent loss and attention diffusion loss. The latent loss aligns the last attention layer between triggered samples and clean samples of the target label. The attention diffusion loss emphasizes the attention diffusion area that encompasses the trigger. A theoretical analysis is provided to underpin the rationale behind the attention diffusion loss. Extensive experiments on CIFAR-10, GTSRB, CIFAR-100, and Tiny ImageNet demonstrate the effectiveness of Megatron. Megatron can achieve attack success rates of over 90% even when the position of the trigger is slightly shifted during testing. Furthermore, Megatron achieves better evasiveness than baselines regarding both human visual inspection and defense strategies (i.e., DBAVT, BAVT, Beatrix, TeCo, and SAGE).

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.04776>)

[PDF](<https://arxiv.org/pdf/2412.04776.pdf>)
