.png){kind=icon}
返回
Interpreting Universal Adversarial Example Attacks on Image Classification Models
.png){kind=icon}
OA
AI
DOI：10.1109/TDSC.2022.3202544.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Mitigating adversarial deep learning attacks remains challenging, partly because of the ease and low cost in carrying out such attacks. Therefore, in this article, we focus on the understanding of universal adversarial example attack on image classification models. Specifically, we seek to understand the difference(s) between adversarial examples in two adversarial datasets (DAmageNet and PGD dataset) and clean examples in ImageNet learned by the classification model, and whether we can use such findings to resist adversarial example attacks. We also seek to determine if we can retrain a discriminator to discriminate whether the input image is an adversarial example, using adversarial training. We then design a number of experiments (e.g., class activation map (CAM) analysis, feature map analysis, feature maps/filters changing, adversarial training, and binary classification model) to help us determine whether the universal adversarial dataset can be successfully used to attack the classification model. This, in turn, contributes to a better understanding of adversarial defenses over pretrained classification model from an interpretation perspective. To the best of our knowledge, this work is one of the earliest works to systematically investigate the interpretation of universal adversarial example attack on image classification models, both visually and quantitatively.
Keyword:
Adversarial defense
adversarial example
deep learning
interpretability
期刊
IF:
7.5
论文数:
2.6K
被引数:
9.6K
机构
暂无机构信息
引用论文
分享收藏Multi-Features Refinement and Aggregation for Medical Brain Segmentation面向医学脑分割的多特征细化与聚合.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI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Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
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Potential-Dependent Reorientation of Water Molecules at an Electrode/Electrolyte Interface Studied by Surface-Enhanced Infrared Absorption Spectroscopy通过表面增强红外吸收光谱法研究的电极/电解质界面上水分子的电位依赖性重新取向
PREAI
分享收藏
查看更多内容