Smart contracts are decentralized applications running on Blockchain. A very large number of smart contracts has been deployed on Ethereum. Meanwhile, security flaws of contracts have led to huge pecuniary losses and destroyed the ecological stability of contract layer on Blockchain. It is thus an emerging yet crucial issue to effectively and efficiently detect vulnerabilities in contracts. Existing detection methods like Oyente and Securify are mainly based on symbolic execution or analysis. These methods are very time-consuming, as the symbolic execution requires the exploration of all executable paths or the analysis of dependency graphs in a contract. In this work, we propose ContractWard to detect vulnerabilities in smart contracts with machine learning techniques. First, we extract bigram features from simplified operation codes of smart contracts. Second, we employ five machine learning algorithms and two sampling algorithms to build the models. ContractWard is evaluated with 49502 real-world smart contracts running on Ethereum. The experimental results demonstrate the effectiveness and efficiency of ContractWard. The predictive Micro-F1 and Macro-F1 of ContractWard are over 96% and the average detection time is 4 seconds on each smart contract when we use XGBoost for training the models and SMOTETomek for balancing the training sets.

In recent years, artificial intelligence has played an increasingly important role in the field of automated control of drones. After AlphaGo used Intensive Learning to defeat the World Go Championship, intensive learning gained widespread attention. However, most of the existing reinforcement learning is applied in games with only two or three moving directions. This paper proves that deep reinforcement learning can be successfully applied to an ancient puzzle game Nokia Snake after further processing. A game with four directions of movement. Through deep intensive learning and training, the Snake (or self-learning Snake) learns to find the target path autonomously, and the average score on the Snake Game exceeds the average score on human level. This kind of Snake algorithm that can find the target path autonomously has broad prospects in the industrial field, such as: UAV oil and gas field inspection, Use drones to search for and rescue injured people after a complex disaster. As we all know, post-disaster relief requires careful staffing and material dispatch. There are many factors that need to be considered in the artificial planning of disaster relief. Therefore, we want to design a drone that can search and rescue personnel and dispatch materials. Current drones are quite mature in terms of automation control, but current drones require manual control. Therefore, the Snake algorithm proposed here to be able to find the target path autonomously is an attempt and key technology in the design of autonomous search and rescue personnel and material dispatching drones.

Internet of Things (IoT) brings the third development wave of the global information industry, which makes users, network, and perception devices cooperate more closely. However, if IoT has security problems, it may cause a variety of damage and even threaten human lives and properties. To improve the abilities of monitoring, providing emergency response, and predicting the development trend of IoT security, a new paradigm called network security situation awareness (NSSA) is proposed. However, it is limited by its ability to mine and evaluate security situation elements from multi-source heterogeneous network security information. To solve this problem, this paper proposes an IoT network security situation awareness model using a situation reasoning method based on semantic ontology and user-defined rules. Ontology technology can provide a unified and formalized description to solve the problem of semantic heterogeneity in the IoT security domain. In this paper, four key sub-domains are proposed to reflect an IoT security situation: context, attack, vulnerability, and network flow. Furthermore, user-defined rules can compensate for the limited description ability of ontology, and hence can enhance the reasoning ability of our proposed ontology model. The examples in real IoT scenarios show that the ability of the network security situation awareness that adopts our situation reasoning method is more comprehensive and more powerful reasoning abilities than the traditional NSSA methods.

The tremendous growth of interconnected things/devices in the whole world advances to the new paradigm i.e. Internet of Things (IoT). The Internet of Things use sensor-based embedded systems to interact with others, providing a wide range of applications and services to upper-level users. Undoubtedly, the data collected by the underlying IoTs is the basis of the upper-layer decision and the foundation for all the applications, which requires efficient energy protocols. Moreover, if the collected data are erroneous and untrustworthy, the data protection and application becomes an unrealistic goal, which further leads to unnecessary energy cost. However, the traditional methods cannot solve this problem efficiently and trustworthily. To achieve this goal, we design a novel energy-efficient and trustworthy protocol based on mobile fog computing. By establishing a trust model on fog elements to evaluate the sensor nodes, the mobile data collection path with the largest utility value is generated, which can avoid visiting unnecessary sensors and collecting untrustworthy data. Theoretical analysis and experimental results validate that our proposed architecture and method outperform traditional data collection methods in both energy and delay.

The number of applications (apps) available for smart devices or Android based IoT (Internet of Things) has surged dramatically over the past few years. Meanwhile, the volume of ill-designed or malicious apps (malapps) has been growing explosively. To ensure the quality and security of the apps in the markets, many approaches have been proposed in recent years to discriminate malapps from benign ones. Machine learning is usually utilized in classification process. Accurately characterizing apps’ behaviors, or so-called features, directly affects the detection results with machine learning algorithms. Android apps evolve very fast. The size of current apps has become increasingly large and the behaviors of apps have become increasingly complicated. Extracting effective and representative features from apps is thus an ongoing challenge. Although many types of features have been extracted in existing work, to the best of our knowledge, no work has systematically surveyed on the features constructed for detecting Android malapps. In this work, we are motivated to provide a clear and comprehensive survey of the state-of-the-art work that detects malapps by characterizing behaviors of apps with various types of features. Through the designed criteria we collect 1947 papers in which 236 papers are used for the survey with four dimensions: the features extracted, the feature selection methods employed if any, the detection methods used, and the scale of evaluation performed. Based on our in-depth survey, we highlight the issues of exploring effective features from apps, provide the taxonomy of these features and indicate the future directions.