Github:https://github.com/TrustAI/DeepCover Task: propose 4 novel test criteria to test DNNs Method: inspired by MC/DC coverage criteria Sign-Sign Coverage(Main): the sign change of a condition feature ψk,independently affects the sign of the decision feature ψk+1,j of the next layer V...
Deep networks perform substantially sub-human even after training on 18 times more images per category compared to the existing large-scale image sets for object classification. We also present a novel analysis-by-synthesis architecture that infers 3D scenes from images via optimization in a ...
Is Neuron Coverage a Meaningful Measure for Testing Deep Neural Networks? image-20201012132512292 本文设计了一个新的多样性促进正则器来注入现有的对抗攻击算法中。然后来评估增加NC的方式生成的测试套件能否使得: 成功的检测对抗性攻击 产生自然的输入 对特定类的预测公正性 基于结果,作者给出的结论是,NC增加反而...
Recent effort to test deep learning systems has produced an intuitive and compelling test criterion called neuron coverage (NC), which resembles the notion of traditional code coverage. NC measures the proportion of neurons activated in a neural network and it is implicitly assumed that increasing NC...
Concolic testing alternates between CONCrete program execution and symbOLIC analysis to explore the execution paths of a software program and to increase code coverage. In this paper, we develop the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we utilise quantifie...
test selection can save labor and then be used to assess the model 前提: the model should have similar prediction accuracy on the data which have similar distances to the decision boundary 本文:Aries Github:https://github.com/wellido/Aries ...
Practical implications: Dissimilarity Metric can be used to guide the similarity-driven adversarial testing procedure of deep neural networks. The results show that in practical testing, to test the effectiveness of targeted attacks, it is sufficient to use target labels with DM≥0.25 for ImageNet...
Hence, deep neural networks must be adequately tested to eliminate as many security risks as possible in some safety-critical software that involves personal and property safety. As the foundation of deep learning systems, deep neural networks should be adequately tested for security. However, deep ...
论文阅读《Knowledge Projection for Effective Design of Thinner and Faster Deep Neural Networks》 本文提出一种新的设定,开始和以前一样,使用一个预训练的大网络来指导一个更窄更快的小网络训练,但是用来训练的数据是新的并且标签信息有限,所以这个场景包括了不同数据域的自适应和模型压缩 加入了一个知识投影矩阵...
Task: Fuzzing Deep Learning Models Github:https://github.com/Shimmer93/Deephunter-backup Method: Metamorphic mutation to generate new semantically preserved tests use multiple plugable coverage criteria as feedback to guide the test generation