.png){kind=icon}
返回
Towards Gradient-Based Saliency Consensus Training for Adversarial Robustness
.png){kind=icon}
PRE
AI
DOI：10.1109/TDSC.2022.3184594.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent works, robust networks have consistently exhibited more discriminative saliency map that proves to indicate sufficient adversarial robustness. In existed safe training paradigms e.g., adversarial training, however, the progressive saliency information regarding on what input semantic feature model prediction relies, have not yet been fully-explored. Due to this, we consider the incorporation of posterior saliency properties of robust model in training, as an efficient supervision signal on robust learning. It thus provides an alternative direction to enhance robustness, from the saliency interpretability perspective. In this article, to harden model we propose to optimize the discrimination of intermediate gradient-based saliency and maintain its consensus in training, which encourage model to behave according to task-relevant feature from the salient region such as object edges in image. Then, we introduce Adversarially Gradient-based Saliency Consensus Training method, dubbed Adv-GSCT. Within it, we preserve the similarity between the learned model saliency and the target one as label, approximated in the most offending case representing the least but essential information scenario. Meanwhile, a constructed pseudo-input coupled with feature importance, is feed into model to ensure the discrimination of estimated target saliency. Besides providing a novel insight into adversarial defense, Adv-GSCT differs from the current most effective adversarial training and does not need multiple iterative generations of adversarial perturbation whose computational cost and sensitivity direction of prediction concern. Finally, extensive performance evaluations on MNIST, CIFAR-10 and ImageNet datasets demonstrate the superiority of our proposed method.
Keyword:
Adversarial robustness
saliency consensus
deep neural networks
期刊
IF:
7.5
论文数:
2.5K
被引数:
9.6K
机构
引用论文
Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏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Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏The Early Cambrian Mianyang-Changning Intracratonic Sag and Its Control on Petroleum Accumulation in the Sichuan Basin, China.png)
Geofluids
OAAI
GeofluidsIF0
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容