Scalable Detection System Research Articles

Hierarchical biomarkers detection via a universal polydopamine probe catalyzed by a hexagonal star-nanostructured DNAzyme

Incompatible cross-platform detection technologies adopted for different medical scenarios has caused several problems in the clinical detection of disease biomarkers. Here, we developed a unified platform with hierarchical performance for biomarker detection. A hexagonal star-nanostructured DNAzyme was constructed. It shows excellent catalytic activity towards the deposition of polydopamine, which is capable of presenting colorimetric signals directly and is also scalable to present fluorescent and electrochemical signals by conjugating with quantum dots. This scalable detection system is validated for the detection of both nucleic acid biomarkers (miRNAs) and protein biomarkers (carcinoembryonic antigen and platelet-derived growth factor). Results show that the detection system can adapt to the current colorimetric, fluorescent and electrochemical equipment, possess the advantage of high efficiency and low-cost, and present hierarchical performance in terms of operability and sensitivity, making it possible to verify the results in a unified system and to switch the detection methods according to different scenarios.

Distinguishing malicious programs based on visualization and hybrid learning algorithms

Modern malware threats demand a robust and scalable detection system. This paper presents a novel proactive monitoring and analysis architecture called malware threat intelligence system (MTIS) to collect and classify real-world samples of modern malware families. Microsoft Window‘s portable executable (PE) files are systematically labeled using clustering and AVClass engine. These labeled malware samples are visualized into grayscale images, which are further utilized for the extraction of textural features. This paper uses local descriptors (LBP, DSIFT, GLCM) and global descriptors(GIST) to extract local and global textural features from a grayscale image. Malware images are distinguished using a hybrid approach of machine learning methods and a proposed convolutional neural network (CNN) employed with early stopping configurations. Results have demonstrated that the proposed architecture detects modern and real-world malware samples with better classification accuracy without code reversing and domain expertise. Four machine learning algorithms, namely, K-nearest neighbors (k-NN), Support vector machine(SVM), Naive Bayes(NB), and Random forest, are compared systematically, with different image resolutions and data split, enabling efficient model selection. Deep learning of MTIS (DL-MTIS) is compared with former methods and with CNN+GIST, CNN with the whole image as inputs, and k-NN+GIST method, and it is observed to be superior in performance. The results also reveal that the proposed method is resilient to packed and encrypted malware samples.