Modern text hiding is an intelligent programming technique which embeds a secret message/watermark into a cover text message/file in a hidden way to protect confidential information. Recently, text hiding in the form of watermarking and steganography has found broad applications in, for instance, covert communication, copyright protection, content authentication, etc. In contrast to text hiding, text steganalysis is the process and science of identifying whether a given carrier text file/message has hidden information in it, and, if possible, extracting/detecting the embedded hidden information. This paper presents an overview of state of the art of the text hiding area, and provides a comparative analysis of recent techniques, especially those focused on marking structural characteristics of digital text message/file to hide secret bits. Also, we discuss different types of attacks and their effects to highlight the pros and cons of the recently introduced approaches. Finally, we recommend some directions and guidelines for future works.

Providing privacy protection for classification algorithms has become a research hotspot in current data mining. In this paper, differential privacy is applied to the random forest classification algorithm, and a random forest algorithm based on differential privacy is proposed to protect the privacy information in the data classification process. Firstly, differential privacy provides privacy protection by adding perturbation noise, which leads to a decrease in the classification accuracy of random forest algorithms. In order to reduce the impact of differential privacy protection on the accuracy of random forest classification, a hybrid decision tree algorithm is proposed. For the construction of a single decision tree in a random forest, the information gain ratio in the ID3 algorithm and the information gain ratio in the C4.5 are combined to generate a new attribute metric IG_GR to improve the classification accuracy of a single decision tree. Secondly, a new privacy budget allocation strategy is proposed. For nodes of different depths in the decision tree, the privacy budget is allocated to its counting query and attribute query by weight, which is used to balance the signal-to-noise ratio of differential privacy technology to nodes of different depths in the decision tree. At the same time, the hybrid decision tree algorithm is applied to the construction of random forest, which balances the privacy and classification accuracy of the random forest algorithm based on differential privacy. Finally, this paper conducted experiments on UCI’s Adult and Mushroom datasets. The results show that compared with the traditional decision tree algorithm, the algorithm proposed in this paper has better classification accuracy; and the DPRF can provide effective privacy protection under the premise of ensuring high classification performance. The work of this paper achieves a balance between privacy and classification accuracy, and has practical application value.

A large number of charging piles installed on roadside parking spaces and smart poles on the roadside of the Internet have become essential substation infrastructure (roadside) for building a vehicle-road coordinated charging network for electric vehicles. The management system of China National Grid's network-load interaction includes the interaction between these main stations (traffic control stations) and substations (roadsides). The Internet-friendly interactive communication protocol for China's vehicle-road coordination is IEC 60870-5-104 (104 protocol). The control network of the vehicle-road collaborative charging network has many characteristics, such as multiple levels, multiple types, and frequent information exchange for monitoring and control. Various types of operational information and control commands are subject to eavesdropping, tampering, and interruption during collection, transmission, and triggering. This paper proposes a command-level anomaly detection (CAD) method for a vehicle-road collaborative charging network. The CAD method analyzes the protocol for the specification format and business command characteristics of the 104 protocol. This paper uses the dynamic analysis protocol fuzzy test to realize the dynamic information in the program to guide the generation of test cases and pass the Markov state transition diagram. We describe the state transition and abnormality identification of protocol messages. We also design a long-term memory network to implement instruction-level anomaly feature mining. The experiment proved the validity of CAD. If we adopt other new protocols for the vehicle-road coordinated network in different countries or regions, the analysis of the new protocol can be completed in the same way, which has strong application value and prospect.

In the trend of continuously advancing urban intelligent transport construction, traditional traffic signal control (TSC) struggles to make effective decisions with complex traffic conditions. Although multi-agent deep reinforcement learning (MARL) shows promise in optimizing traffic flow, most existing studies ignore the complex relationships between signal lights and fail to communicate with neighbors effectively. Moreover, the deterministic strategies generated by Q-learning-based methods struggle to be extended to large-scale urban road networks. Therefore, this paper proposes a multi-agent graph-based soft actor-critic (MAGSAC) approach for TSC, which combines graph neural networks with the Soft Actor-Critic (SAC) algorithm and extends it to multi-agent environments to address the TSC problem. Specifically, we employ graph-based networks and attention mechanism to expand the receptive domain of agents, enable environmental information to be shared among agents, and utilize the attention mechanism to filter out unimportant information. The algorithm adheres to the Centralized Training Decentralized Execution (CTDE) paradigm to minimize the non-stationarity of MARL. Finally, a rigorous experimental evaluation was conducted using the CityFlow simulator on both synthetic traffic grids and real-world urban road networks. Experimental results show that MAGSAC outperforms other TSC methods in performance metrics, including average queue length and waiting time, and achieves excellent performance under complex urban traffic conditions.

The real-time and high-continuity requirements of the edge computing network gain more and more attention because of its active defence problem, that is, a data-driven complex problem. Due to the dual constraints of the hybrid feature of edge computing networks and the uncertainty of new attack features, implementing active defence measures such as detection, evasion, trap, and control is essential for the security protection of edge computing networks with high real-time and continuity requirements. The basic idea of safe active defence is to make the defence gain more significant than the attack loss. To encounter the new attacks with uncertain features introduced by the ubiquitous transmission network in the edge computing network, this paper investigates the attack behaviour and presents an attack-defence mechanism based on game theory. Based on the idea of dynamic intrusion detection, we utilize the game theory in the field of edge computing network and suggest a data-driven mimicry intrusion detection game model-based technique called GLIDE. The game income of participants and utility computing methods under different deployment strategies are analysed in detail. According to the proof analysis of the Nash equilibrium condition in the model, the contradictory dynamic game relationship is described. Therefore, the optimal deployment strategy of the multiredundancy edge computing terminal intrusion detection service in the edge computing network is obtained by solving the game balance point. The detection probability of the edge computing network for network attacks is improved, and the cost of intrusion detection of the edge computing network is reduced.