Password guessing is an important issue in user security and privacy protection. Using generative adversarial network (GAN) to guess passwords is a new strategy emerging in recent years, which exploits the discriminator’s evaluation of passwords to guide the update of the generator so that password guessing sets can be produced. However, the sampling process of discrete data from a categorical distribution is not differentiable so that backpropagation does not work well. In this paper, we propose a novel password guessing model named G-Pass, which consists of two main components. The first is a new network structure, which modifies the generator from the convolutional neural network (CNN) to long short-term memory- (LSTM-) based network and employs multiple convolutional layers in the discriminator to provide more informative signals for generator updating. The second is Gumbel-Softmax with temperature control for training GAN on passwords. Experimental results show the proposed G-Pass outperforms PassGAN in password quality and cracking rate. Moreover, by dynamically adjusting one parameter during the training process, a trade-off between sample diversity and quality can be achieved with our proposed model.
Since the nineteen nineties, high strength concrete technology was developing rapidly in our country. However, high-strength concrete detection technology is relatively backward. According to the characteristic of the pumping concrete in Tangshan area and the requirements of JGJ/T23-2001, The paper adopted representative materials of Tangshan to divide high strength concrete test blocks which strength grade is from C50 to C80 into 4 ages of 14 days, 28 days, 60 days and 90 days, then adopted high strength concrete rebound apparatus to experimental research by the rebound method. At last, the test data was collected, and applied regression analysis theory, then used the principle of least square method for regression analysis. The optimal pumping concrete strength rebound curve formula could be obtained.
With the average daily growth of 15000 new subscribers, the number of WeChat subscription has broken the 5,800,000 subscribers recently. WeChat subscription's topic influence calculation has been very significant. This article takes Tencent-WeChat subscription platform as the research object and focuses on the influence analysis of topic diffusion. Based on the subscription's temporal characteristics of influence, the parameters of propagation capability, and the similarity weights among different subscriptions with the same topic, the authors propose an analysis model of WeChat subscription influence.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.