.png){kind=icon}
返回
Lagrangian objective function leads to improved unforeseen attack generalization
.png){kind=icon}
PRE
AI
DOI：10.1007/s10994-023-06348-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent improvements in deep learning models and their practical applications have raised concerns about the robustness of these models against adversarial examples. Adversarial training (AT) has been shown effective in reaching a robust model against the attack that is used during training. However, it usually fails against other attacks, i.e., the model over fits to the training attack scheme. In this paper, we propose a new method for generating adversarial perturbations during training that mitigates the mentioned issue. More specifically, we minimize the perturbation l(p) norm while maximizing the classification loss in the Lagrangian form to craft adversarial examples. We argue that crafting adversarial examples based on this scheme results in enhanced attack generalization in the learned model. We compare our final model robust accuracy with the closely related state-of-the-art AT methods against attacks that were not used during training. This comparison demonstrates that our average robust accuracy against unseen attacks is 5.9% higher in the CIFAR-10 dataset and 3.2% higher in the ImageNet-100 dataset than corresponding state-of-the-art methods. We also demonstrate that our attack is faster than other attack schemes that are designed for unseen attack generalization and conclude that the proposed method is feasible for large datasets. Our code is available at https://github.com/rohban-lab/Lagrangian_Unseen.
Keyword:
Adversarial training
Defense
Lagrange multiplier
Unforeseen attacks
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Early signs of neuronal apoptosis in the substantia nigra pars compacta of the progressive neurodegenerative mouse 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine/probenecid model of Parkinson’s disease.png)
Neuroscience
NeuroscienceIF0
PREAI
分享收藏
A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies模式识别中的强大对抗训练综述: 基础、理论和方法PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容