- 年份
- 2021(1)
- 学科
共检索到1条记录
发布时间倒序
- 发布时间倒序
- 相关度优先
文献计量分析
- 结果分析(前20)
- 结果分析(前50)
- 结果分析(前100)
- 结果分析(前200)
- 结果分析(前500)
[期刊] Tsinghua Science and Technology
[作者]
Keji Han Yun Li Bin Xia
Deep Neural Networks(DNNs) are demonstrated to be vulnerable to adversarial examples, which are elaborately crafted to fool learning models. Since the accuracy and robustness of DNNs are at odds for the adversarial training method, the adversarial example detection algorithms check whether the specific example is adversarial, which is promising to solve the issue of the adversarial example. However, among the existing methods,model-aware detection methods do not generalize well, while the detection accuracies of the generative-based methods are lower compared to the model-aware methods. In this paper, we propose a cascade model-aware generative adversarial example detection method, namely CMAG. CMAG consists of two first-order reconstructors and a second-order reconstructor, which can illustrate what the model sees to the human by reconstructing the logit and feature maps of the last convolution layer. Experimental results demonstrate that our method is effective and is more interpretable compared to some state-of-the-art methods.
文献操作()
导出元数据
文献计量分析
导出文件格式：WXtxt
删除
推荐搜索
A Deep Learning Method for Chinese Singer Identification
Deep Model Compression for Mobile Platforms:A Survey
A Method for Predicting Service Deprecation in Service Systems
Linz-a modern center of economy and a social model city
A Novel Routing Method for Social Delay-Tolerant Networks
A Novel Hybrid Method to Analyze Security Vulnerabilities in Android Applications
A Generative Method for Steganography by Cover Synthesis with Auxiliary Semantics
Building a Post-Layout Simulation Performance Model with Global Mapping Model Fusion Technique
A Novel Multilevel Index Model for Distributed Service Repositories
A New Method of Portfolio Optimization Under Cumulative Prospect Theory
