No abstract

No abstract

Ethereum is one of the currently popular trading platform, where any one can exchange, buy, or sell cryptocurrencies. Smart contract, a computer program, can help Ethereum to encode rules or scripts for processing transactions.Because the smart contract usually handles large number of cryptocurrencies worth billions of dollars apiece, its security has gained considerable attention.In this paper, we first investigate the security of smart contracts running on the Ethereum and introduce several new security vulnerabilities that allow adversaries to exploit and gain financial benefits. Then, we propose a more practical smart contract analysis tool termed NeuCheck, in which we introduce the syntax tree in the syntactical analyzer to complete the transformation from source code to intermediate representation, and then adopt the open source library working with XML to analyze such tree. We have built a prototype of NeuCheck for Ethereum and evaluate it with over 52 000 existing Ethereum smart contracts. The results show that (1) our new documented vulnerabilities are prevalent;(2) NeuCheck improves the analysis speed by at least 17.2 times compared to other popular analysis tools (eg, Securify and Mythril; and (3) allows for cross-platform deployment.

Summary The number of malware has exploded due to the openness of the Android platform, and the endless stream of malware poses a threat to the privacy, tariffs, and device of mobile phone users. A novel Android mobile malware detection system is proposed, which employs an optimized deep convolutional neural network to learn from opcode sequences. The optimized convolutional neural network is trained multiple times by the raw opcode sequences extracted from the decompiled Android file, so that the feature information can be effectively learned and the malicious program can be detected more accurately. More critically, the k‐max pooling method with better results is adopted in the pooling operation phase, which improves the detection effect of the proposed method. The experimental results show that the detection system achieved the accuracy of 99%, which is 2%‐11% higher than the accuracy of the machine learning detection algorithms when using the same data set. It also ensures that the indicators, such as F1‐score, recall, and precision, are maintained above 97%. Based on the detection system, a multi–data set comparison experiment is carried out. The introduced k‐max pooling is deeply studied, and the effect of k of k‐max pooling on the overall detection effect is observed.