Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion
Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Networks (CNN) across various computer vision tasks. However, akin to CNN, ViTs are vulnerable to backdoor attacks, where the adversary embeds the backdoor into the victim model, causing it to make wrong predictions about testing samples containing a specific trigger. Existing backdoor attacks against ViTs have the limitation of failing to strike an optimal balance between attack stealthiness and attack effectiveness. In this work, we propose an Attention Gradient-based Erosion Backdoor (AGEB) targeted at ViTs. Considering the attention mechanism of ViTs, AGEB selectively erodes pixels in areas of maximal attention gradient, embedding a covert backdoor trigger. Unlike previous backdoor attacks against ViTs, AGEB achieves an optimal balance between attack stealthiness and attack effectiveness, ensuring the trigger remains invisible to human detection while preserving the model's accuracy on clean samples. Extensive experimental evaluations across various ViT architectures and datasets confirm the effectiveness of AGEB, achieving a remarkable Attack Success Rate (ASR) without diminishing Clean Data Accuracy (CDA). Furthermore, the stealthiness of AGEB is rigorously validated, demonstrating minimal visual discrepancies between the clean and the triggered images.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackHuman DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
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 wrong…
Backdoor AttackAn Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers
Recent studies have revealed the vulnerability of Deep Neural Network (DNN) models to backdoor attacks. However, existing backdoor attacks arbitrarily set the trigger mask or use a randomly selected trigger, which restri…
Backdoor AttackYou Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?
Vision Transformers (ViTs), which made a splash in the field of computer vision (CV), have shaken the dominance of convolutional neural networks (CNNs). However, in the process of industrializing ViTs, backdoor attac…
Backdoor AttackDBIA: Data-free Backdoor Injection Attack against Transformer Networks
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…
Backdoor Attackimage-classificationImage ClassificationvalidPASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger loc…