The widespread adoption of encrypted communication protocols has significantly enhanced network security and user privacy, simultaneously elevating the importance of encrypted traffic analysis across various domains, including network anomaly detection. The Transport Layer Security (TLS) 1.3 protocol, introduced in 2018, has gained rapid popularity due to its enhanced security features and improved performance. However, TLS 1.3’s security enhancements, such as encrypting more of the handshake process, present unprecedented challenges for encrypted traffic analysis, rendering traditional methods designed for TLS 1.2 and earlier versions ineffective and necessitating the development of novel analytical techniques. This comprehensive survey provides a thorough review of the latest advancements in TLS 1.3 traffic analysis. First, we examine the impact of TLS 1.3’s new features, including Encrypted ClientHello (ECH), 0-RTT session resumption, and Perfect Forward Secrecy (PFS), on existing traffic analysis techniques. We then present a systematic overview of state-of-the-art methods for analyzing TLS 1.3 traffic, encompassing middlebox-based interception, searchable encryption, and machine learning-based approaches. For each method, we provide a critical analysis of its advantages, limitations, and applicable scenarios. Furthermore, we compile and review key datasets utilized in machine learning-based TLS 1.3 traffic analysis research. Finally, we discuss the main challenges and potential future research directions for TLS 1.3 traffic analysis. Given that TLS 1.3 is still in the early stages of widespread deployment, research in this field remains nascent. This survey aims to provide researchers and practitioners with a comprehensive reference, facilitating the development of more effective TLS 1.3 traffic analysis techniques that balance network security requirements with user privacy protection.

Emerging intelligent systems rely on secure and efficient signal processing to ensure reliable operation in environments where there is limited prior knowledge and significant interference. Single-channel blind source separation (SCBSS) is critical for applications such as wireless communication and sensor networks, where signals are often mixed and corrupted. Variational mode decomposition (VMD) has proven effective for SCBSS, but its performance depends heavily on selecting the optimal modal component count k and quadratic penalty parameter $\alpha$. To address this challenge, we propose a secure and intelligent SCBSS algorithm leveraging adaptive VMD optimized with Improved Particle Swarm Optimization (IPSO). The IPSO dynamically determines the optimal k and $\alpha$ parameters, enabling VMD to filter noise and create a virtual multi-channel signal. This signal is then processed using improved Fast Independent Component Analysis (IFastICA) for high-fidelity source isolation. Experiments on the RML2016.10a dataset demonstrate a 15.7% improvement in separation efficiency over conventional methods, with robust performance for BPSK and QPSK signals, achieving correlation coefficients above 0.9 and signal-to-noise ratio (SNR) improvements of up to 24.66 dB.

Claim extraction and decontextualization are fundamental steps in automated fact-checking tasks. Claim extraction aims to identify core check-worthy claims from unverified text, while decontextualization seeks to eliminate the contextual dependencies of core claims so that they can be understood independently of the original text. In practical applications, information to be verified is usually presented in the form of documents, and existing document-level claim extraction and decontextualization methods often rely on complex multi-model architectures. This paper proposes LLM-CED, a document-level claim extraction and decontextualization method based on large language models, which consists of four modules: core-claim extraction, ambiguous-unit identification and question generation, question-answering-driven decontextualization, and self-reflective review. By using a single general-purpose LLM as the shared underlying model across all stages, LLM-CED reduces model heterogeneity and simplifies the integration and coordination of different processing stages. Experiments on the AVeriTeC-DCE dataset show that LLM-CED outperforms the evaluated baseline methods in document-level claim extraction, decontextualization, and the overall task. For the overall document-level claim extraction and decontextualization task, LLM-CED achieves a chrF score of 33.52% under the top-three evaluation setting.