Network traffic classification is essential for application identification and malicious behavior detection. However, the widespread use of encryption protocols hides payloads and reduces the availability of high-quality labeled data, both of which constrain the effectiveness of current models. To address these challenges, we propose CL-ViME, a self-supervised encrypted traffic classification framework that integrates Contrastive Learning and Vision Mixture of Experts. First, we design a packet-temporal matrix that preserves fine-grained packet headers and flow-level temporal structure. Second, we introduce a Vertical Vision Transformer-Mixture of Experts model to extract dual-view features through vertical patching and dynamic expert routing. Third, we develop a dual-granularity contrastive learning framework that aligns packet-level and flow-level representations via an MoE projector, followed by lightweight classifier-head fine-tuning. Experiments on three public datasets show that CL-ViME significantly outperforms state-of-the-art self-supervised and supervised baselines across accuracy, macro-precision, macro-recall, and macro-F1. It also demonstrates strong generalization and stability.

With the widespread use of Internet in daily life, the scale of network traffic has shown an explosive growth trend. However, malicious activities such as cyberattacks have a severe impact on cybersecurity. An effective countermeasure is to detect abnormal traffic from large-scale network traffic to maintain cybersecurity, but traditional abnormal traffic detection methods are unable to effectively handle current complex and diverse network traffic. The development of artificial intelligence has provided an effective solution, but its performance is influenced by the quality of extracted features. To accurately detect abnormal traffic, this paper proposes a feature extraction method called AD-CAE for network traffic based on a symmetric deep convolutional autoencoder. Firstly, raw network traffic is preprocessed by z-score normalization to transform into the format that can be easily handled by ADCAE model. Then, the multilayer convolution of ADCAE is used to hierarchically extract the features, and the step-size compression strategy of spatial dimension is used to preserve the spatial structure information as well as enlarge the sensory field. Finally, a convolutional block attention module (CBAM) is added at the end of encoder to highlight the key features by learning channel weights through global pooling and fully connected layers. Experimental results on two widely used network traffic datasets show that the features extracted by ADCAE achieve better performance on three detection models.

Blockchain provides new technologies and ideas for the construction of agricultural product traceability system (APTS). However, if data is stored, supervised, and distributed on a multiparty equal blockchain, it will face major security risks, such as data privacy leakage, unauthorized access, and trust issues. How to protect the privacy of shared data has become a key factor restricting the implementation of this technology. We propose a secure and trusted agricultural product traceability system (BCST-APTS), which is supported by blockchain and CP-ABE encryption technology. It can set access control policies through data attributes and encrypt data on the blockchain. This can not only ensure the confidentiality of the data stored in the blockchain, but also set flexible access control policies for the data. In addition, a whole-chain attribute management infrastructure has been constructed, which can provide personalized attribute encryption services. Furthermore, a reencryption scheme based on ciphertext-policy attribute encryption (RE-CP-ABE) is proposed, which can meet the needs of efficient supervision and sharing of ciphertext data. Finally, the system architecture of the BCST-APTS is designed to successfully solve the problems of mutual trust, privacy protection, fine-grained, and personalized access control between all parties.