.png){kind=icon}
返回
Common knowledge learning for generating transferable adversarial examples
.png){kind=icon}
PRE
AI
DOI：10.1007/s11704-024-40533-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples using a substitute (source) model and utilizes them to attack an unseen target model, without knowing its information. Existing methods tend to give unsatisfactory adversarial transferability when the source and target models are from different types of DNN architectures (e.g., ResNet-18 and Swin Transformer). In this paper, we observe that the above phenomenon is induced by the output inconsistency problem. To alleviate this problem while effectively utilizing the existing DNN models, we propose a common knowledge learning (CKL) framework to learn better network weights to generate adversarial examples with better transferability, under fixed network architectures. Specifically, to reduce the model-specific features and obtain better output distributions, we construct a multi-teacher framework, where the knowledge is distilled from different teacher architectures into one student network. By considering that the gradient of input is usually utilized to generate adversarial examples, we impose constraints on the gradients between the student and teacher models, to further alleviate the output inconsistency problem and enhance the adversarial transferability. Extensive experiments demonstrate that our proposed work can significantly improve the adversarial transferability.
Keyword:
black-box attack
adversarial transferability
deep neural networks
期刊
IF:
4.6
论文数:
1.6K
被引数:
2.8K
机构
引用论文
分享收藏The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏A prompt-based approach to adversarial example generation and robustness enhancement基于提示的对抗示例生成和鲁棒性增强方法
PREAI
分享收藏Adversarial example generation with adabelief optimizer and crop invariance.png)
APPLIED INTELLIGENCE
OAAI
APPLIED INTELLIGENCEIF3.5
OAAI分享收藏AutoMA: Towards Automatic Model Augmentation for Transferable Adversarial AttacksAutoMA: 针对可转移的对抗攻击的自动模型增强
PREAI
分享收藏
查看更多内容