Search

Anomaly detection for network traffic aims to analyze the characteristics of network traffic in order to discover unknown attacks. Currently, existing detection methods have achieved promising results against high-intensity attacks that aim to interrupt the operation of the target system. In reality, attack behaviors that are commonly exhibited are highly concealed and disruptive. In addition, the attack scales are flexible and variable. In this paper, we construct a multiscale network intrusion behavior dataset, which includes three attack scales and two multiscale attack patterns based on probability distribution. Specifically, we propose a stacked ensemble learning-based detection model for anomalous traffic (or SEDAT for short) to defend against highly concealed multiscale attacks. The model employs a random forest (RF)-based method to select features and introduces multiple base learning autoencoders (AEs) to enhance the representation of multiscale attack behaviors. In addressing the challenge of a single model's inability to capture the regularities of multiscale attack behaviors, SEDAT is capable of adapting to the complex multiscale characteristics in network traffic, enabling the prediction of network access behavior. Comparative experiments demonstrate that SEDAT exhibits superior detection capabilities in multiscale network attacks. In particular, SEDAT achieves an improvement of at least 5% accuracy over baseline methods for detecting multiscale attacks. [ABSTRACT FROM AUTHOR]

Background: Ferroptosis, a form of regulated cell death associated with iron-dependent lipid peroxidation, plays a role in cancer progression. However, the specific mechanisms of ferroptosis in lung adenocarcinoma (LUAD) bone metastasis (BM) remain unclear. Using bioinformatics analysis, this study sought to identify the ferroptosis-associated genes involved in BM in LUAD, thus providing potential novel targets for the treatment of BM in LUAD., Methods: The RNA expression dataset GSE10799 was acquired from the Gene Expression Omnibus (GEO) database, and intersected with the ferroptosis dataset to identify ferroptosis-related differentially expressed genes (DEGs). The expression of candidate genes and their correlation with the prognosis of LUAD patients were validated in The Cancer Genome Atlas (TCGA) database. A protein gene interaction network was constructed using GeneMania and Retrieval of Interacting Genes/Proteins (STRING) databases. The association between the candidate genes and immune cells was assessed via TCGA and Tumor IMmune Estimation Resource (TIMER) databases. The potential mechanisms were elucidated by a gene set enrichment analysis (GSEA). The relevant microRNAs (miRNAs or miRs) that bind to the 3'untranslated region (3'UTR) end of candidate genes' mRNA was explored using the TargetScan database. The expression of these candidate miRNAs in LUAD was validated and the correlation between candidate miRNAs and candidate mRNAs was tested using the TCGA database. Finally, the clinical data of 40 LUAD patients were retrospectively analyzed to evaluate the clinical value of candidate gene expression for LUAD BM patients., Results: In this research, 15 ferroptosis-related DEGs in LUAD BM were identified. TCGA database analysis indicated that patients with low levels of CDGSH iron-sulfur domain 2 ( CISD2 ) in LUAD had better disease-specific survival (DSS), overall survival (OS), and a better progression-free interval (PFI) than those with high levels of CISD2 . The TIMER database results show that the expression of CISD2 is correlated with the infiltration levels of various immune cells. The GSEA indicated that CISD2 might influence biological activity in LUAD by participating in cell-cycle regulation, mitochondrial translation, DNA damage repair, c- Myc ( MYC ) activation, and the P53 signaling pathway. Through the combined analysis of the TargetScan and TCGA databases, hsa-miR-320a was identified as the optimal upstream regulatory miRNA. The immunohistochemistry data indicated that the positive CISD2 expression rates and immunohistochemistry scores of the patients with BM were significantly higher than those of the patients without BM (P<0.05). The high expression of CISD2 is a significant risk factor for BM in LUAD., Conclusions: The downregulation of CISD2 expression may extend DSS, OS, and the PFI of LUAD patients. Thus, CISD2 could serve as a novel predictive biomarker for LUAD patients. Further, miR-320a might negatively regulate CISD2 and participate in LUAD BM by activating MYC . These data provide a potential perspective for developing anticancer therapies for LUAD-BM patients., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://tcr.amegroups.com/article/view/10.21037/tcr-24-1188/coif). The authors have no conflicts of interest to declare., (2024 Translational Cancer Research. All rights reserved.)