Preventing network intrusion is the essential requirement of network security. In recent years, people have conducted a lot of research on network intrusion detection systems. However, with the increasing number of advanced threat attacks, traditional intrusion detection mechanisms have defects and it is still indispensable to design a powerful intrusion detection system. This paper researches the NSL-KDD data set and analyzes the latest developments and existing problems in the field of intrusion detection technology. For unbalanced distribution and feature redundancy of the data set used for training, some training samples are under-sampling and feature selection processing. To improve the detection effect, a Deep Stacking Network model is proposed, which combines the classification results of multiple basic classifiers to improve the classification accuracy. In the experiment, we screened and compared the performance of various mainstream classifiers and found that the four models of the decision tree, k-nearest neighbors, deep neural network and random forests have outstanding detection performance and meet the needs of different classification effects. Among them, the classification accuracy of the decision tree reaches 86.1%. The classification effect of the Deeping Stacking Network, a fusion model composed of four classifiers, has been further improved and the accuracy reaches 86.8%. Compared with the intrusion detection system of other research papers, the proposed model effectively improves the detection performance and has made significant improvements in network intrusion detection.

With the development of deepfake technology, deepfake detection has received widespread attention. Although some deepfake forensics techniques have been proposed, they are still very difficult to implement in real-world scenarios. This is due to the differences in different deepfake technologies and the compression or editing of videos during the propagation process. Considering the issue of sample imbalance with few-shot scenarios in deepfake detection, we propose a multi-feature channel domain-weighted framework based on meta-learning (MCW). In order to obtain outstanding detection performance of a cross-database, the proposed framework improves a meta-learning network in two ways: it enhances the model’s feature extraction ability for detecting targets by combining the RGB domain and frequency domain information of the image and enhances the model’s generalization ability for detecting targets by assigning meta weights to channels on the feature map. The proposed MCW framework solves the problems of poor detection performance and insufficient data compression resistance of the algorithm for samples generated by unknown algorithms. The experiment was set in a zero-shot scenario and few-shot scenario, simulating the deepfake detection environment in real situations. We selected nine detection algorithms as comparative algorithms. The experimental results show that the MCW framework outperforms other algorithms in cross-algorithm detection and cross-dataset detection. The MCW framework demonstrates its ability to generalize and resist compression with low-quality training images and across different generation algorithm scenarios, and it has better fine-tuning potential in few-shot learning scenarios.

With the frequent occurrence of network security events, the intrusion detection system will generate alarm and log records when monitoring the network environment in which a large number of log and alarm records are redundant, which brings great burden to the server storage and security personnel. How to reduce the redundant alarm records in network intrusion detection has always been the focus of researchers. In this paper, we propose a method using the whale optimization algorithm to deal with massive redundant alarms. Based on the alarm hierarchical clustering, we integrate the whale optimization algorithm into the process of generating alarm hierarchical clustering and optimizing the cluster center and put forward two versions of local hierarchical clustering and global hierarchical clustering, respectively. To verify the feasibility of the algorithm, we conducted experiments on the UNSW-NB15 data set; compared with the previous alarm clustering algorithms, the alarm clustering algorithm based on the whale optimization algorithm can generate higher quality clustering in a shorter time. The results show that the proposed algorithm can effectively reduce redundant alarms and reduce the load of IDS and staff.

To detect stego (steganographic text) in complex scenarios, linguistic steganalysis (LS) with various motivations has been proposed and achieved excellent performance. However, with the development of generative steganography, some stegos have strong concealment, especially after the emergence of LLMsbased steganography, the existing LS has low detection or cannot detect them. We designed a novel LS with two modes called LSG/C. In the generation mode, we created an LS-task “description” and used the generation ability of LLM to explain whether texts to be detected are stegos. On this basis, we rethought the principle of LS and LLMs, and proposed the classification mode. In this mode, LS-G/C deleted the LS-task “description” and used the “causalLM” LLMs to extract steganographic features. The LS features can be extracted by only one pass of the model, and a linear layer with initialization weights is added to obtain the classification probability. Experiments on strongly concealed stegos show that LS-G/C significantly improves detection and reaches SOTA performance. Additionally, LS-G/C in classification mode greatly reduces training time while maintaining high performance.

Intelligent transportation systems (ITS) use advanced technologies such as artificial intelligence to significantly improve traffic flow management efficiency, and promote the intelligent development of the transportation industry. However, if the data in ITS is attacked, such as tampering or forgery, it will endanger public safety and cause social losses. Therefore, this paper proposes a watermarking that can verify the integrity of copyright in response to the needs of ITS, termed ITSmark. ITSmark focuses on functions such as extracting watermarks, verifying permission, and tracing tampered locations. The scheme uses the copyright information to build the multi-bit space and divides this space into multiple segments. These segments will be assigned to tokens. Thus, the next token is determined by its segment which contains the copyright. In this way, the obtained data contains the custom watermark. To ensure the authorization, key parameters are encrypted during copyright embedding to obtain cipher data. Only by possessing the correct cipher data and private key, can the user entirely extract the watermark. Experiments show that ITSmark surpasses baseline performances in data quality, extraction accuracy, and unforgeability. It also shows unique capabilities of permission verification and tampered location tracing, which ensures the security of extraction and the reliability of copyright verification. Furthermore, ITSmark can also customize the watermark embedding position and proportion according to user needs, making embedding more flexible.