ABSTRACT Smart contract transactions are increasingly interspersed with cross‐contract calls, creating intricate vulnerabilities that current tools frequently neglect. Cross‐contract vulnerabilities, stemming from interactions among many contracts, are notably difficult to identify, as existing methodologies are restricted to the analysis of only two contracts simultaneously. The growing number of transaction sequences and the larger area to search due to multiple contracts working together make it very hard to find these vulnerabilities. Traditional fuzzing methods are good at finding simple errors within a single contract, but they struggle to detect problems that come from complex interactions between multiple contracts, such as how they call each other and depend on each other's states. This work presents CrossGuard, a fuzz testing‐based approach aimed at effectively identifying cross‐contract vulnerabilities by addressing the shortcomings of conventional tools. Instead of using random transaction sequences like earlier fuzzers, CrossGuard uses smart fuzzing that learns from large language models (LLMs) to better explore important paths. We evaluate CrossGuard against top tools like CrossFuzz and xFuzz using 500 cross‐contracts that have vulnerabilities such as reentrancy, integer overflow, and block dependency. CrossGuard consistently achieves higher coverage and excels at detecting reentrancy and block dependency vulnerabilities. However, its performance on integer overflow detection is currently lower than that of CrossFuzz; this contrast underscores both the potential and the current limitations of LLM‐guided fuzzing. Natural language reasoning is highly effective for path‐sensitive, stateful vulnerabilities, but less precise for numeric edge cases where mutational fuzzing remains strong.

Due to the rapid propagation and significant impact, the network public opinion of hot topics has become a concern of the social public and governments. The existing models based on the evolutionary game cannot reflect the real-world propagation of hot topics under uncertain environmental interference. And few researchers analyze the early intervention timing of the government on hot topics based on stochastic evolutionary game theory. To solve these problems, the government intervention parameters of punishment intensity, intervention delay, and intervention probability are introduced to build a three-party stochastic evolutionary game model of “media-netizen-government” in the multi-agent system under the scene of hot topics propagation. Then, the stochastic differential equation is expanded and simulated by the explicit forward Euler numerical method. Finally, simulation experiments are conducted to quantitatively analyze the random evolutionary process and the government intervention timing by adjusting key parameters, which can provide the optimal timing and suggestions for governments to intervene in hot topics propagation.

As an advantageous technique and service, the blockchain has shown great development and application prospects. However, its security has also met great challenges, and many security vulnerabilities and attack issues in blockchain-based services have emerged. Recently, security issues of blockchain have attracted extensive attention. However, there is still a lack of blockchain security research from a full-stack architecture perspective, as well as representative quantitative experimental reproduction and analysis. We aim to provide a security architecture to solve security risks in blockchain services from a full-stack architecture perspective. Meanwhile, we propose a formal definition of the full-stack security architecture for blockchain-based services, and we also propose a formal expression of security issues and defense solutions from a full-stack security perspective. We use ConCert to conduct a smart contract formal verification experiment by property-based testing. The security vulnerabilities of blockchain services in the Common Vulnerabilities and Exposures (CVE) and China Nation Vulnerability Database (CNVD) are selected and enumerated. Additionally, three real contract-layer real attack events are reproduced by an experimental approach. Using Alibaba's blockchain services and Identity Mixer in Hyperledger Fabric as a case study, the security problems and defense techniques are analyzed and researched. At last, the future research directions are proposed.

Aiming at the problem of DDoS attack detection in internet of things (IoT) environment, statistical and machine-learning algorithms are proposed to model and analyze the network traffic of DDoS attack. Docker-based virtualization platform is designed and configured to collect IoT network traffic data. Then the packet-level, flow-level, and second-level network traffic datasets are generated, and the importance of features in different traffic datasets are sorted. By SKlearn and TensorFlow machine-learning software framework, different machine learning algorithms are researched and compared. In packet-level DDoS attack detection, KNN algorithm achieves the best results; the accuracy is 92.8%. In flow-level DDoS attack detection, the voting algorithm achieves the best results; the accuracy is 99.8%. In second-level DDoS attack detection, the RNN algorithm behaves best results; the accuracy is 97.1%. The DDoS attack detection method combined with statistical analysis and machine-learning can effectively detect large-scale DDoS attacks on the internet of things simulation experimental environment.

Low‐rate denial of service (LDoS) attack is a special DoS attack type of wireless sensor network (WSN). Routing protocol is the critical component of the WSN. Routing flood attack is a novel LDoS attack pattern in WSN. However, the attack is difficult to be detected by traditional intrusion detection algorithm. A novel LDoS attack detection method based on big data and signal analysis is proposed. Hilbert–Huang Transform (HHT) time–frequency signal analysis method is used to analyse the small non‐linear signal from LDoS attack traffic signal. Spark‐based Pearson and Spearman correlation coefficient calculation approaches are used to recognise the false intrinsic mode functions (IMFs) components decomposed by the HHT method. The effective threshold value of Pearson correlation coefficient is set to 0.2, the effective threshold value of Spearman correlation coefficient is set to 0.3, which are united to identify the false IMF components. SunSpot wireless nodes are used to build the wireless sensor nodes. If the difference between the IMF component and the normal IMF component is more than 40%, the LDoS attack will be detected. Experimental results show that this approach is effective to detect the LDoS attack in ZigBee WSN. This is a quantitative LDoS attack detection experimental research in WSN.

Ransomware techniques have evolved over time with the most resilient attacks making data recovery practically impossible. This has driven countermeasures to shift towards recovery against prevention but in this paper, we model ransomware attacks from an infection vector point of view. We follow the basic infection chain of crypto ransomware and use Bayesian network statistics to infer some of the most common ransomware infection vectors. We also employ the use of attack and sensor nodes to capture uncertainty in the Bayesian network.

In 3G mobile communication system, mobile broadband data services create great opportunities on revenue growth for network carriers. In the mean time, the dramatically increased subscribers make the access and core network more and more over-loaded everyday. Unfortunately, majority of wireless bandwidth is consumed by non revenue driven application traffic such as the P2P downloading, illegal VoIP and file sharing that launched by minority of subscribers. This phenomenon seriously affects the experience of normal users. From the perspective of network carriers, network performance and user behavior should be monitored to detect mis-conducts and abnormal utilization in real time so as to achieve utilization fairness and efficiency. In this paper, we implement the deep packet inspection (DPI) technology into the CDMA 1x EV DO mobile network packet switch (PS) domain and construct a DPI based network traffic monitoring, analysis and management system. With the system, subscriber, cell, base station, PCF and PDSN based traffic monitoring and control, and application based traffic management is enabled. As a result, network capacity has been fully utilized by setting the application rate threshold, customer satisfaction has been greatly improved by keeping fair bandwidth utilization.