No abstract

With the widespread use of computers, the amount of malware has increased exponentially. Since dynamic detection is costly in both time and resources, most existing malware detection methods are based on static features. However, existing static methods mainly rely on single feature types of malware, while few pay attention to multi-feature fusion. This paper presents a novel multi-feature extraction and fusion method to effectively detect malware variants by combining binary and opcode features. We propose a stacked convolutional network to capture the temporal and discontinuity information in the function call of the binary file from malware. Additionally, we adopt the triangular attention algorithm to extract code-level features from assembly code. Additionally, these two extracted features are aligned and fused by the cross-attention, which could provide a stable feature representation. We evaluate our method on two different datasets. It achieves an accuracy of 0.9954 on the Kaggle Malware Classification dataset and an accuracy of 0.9544 on a large real-world dataset. To optimize our detection model, we conduct in-depth discussions on different feature extractors and multi-feature fusion strategies. Moreover, a visualized attention module in our model is provided to explain its superiority in the opcode feature extraction. An experimental analysis is performed against five baseline deep learning models and five state-of-the-art malware detection models, which reveals that our strategy outperforms competing approaches in all evaluation circumstances.

Inulin-type fructooligosaccharides (FOSs) constitute an abundant subgroup of fructans with important biological activities. However, the availability of individual fructooligosaccharides with an accurate structure in high purity and quality remains challenging. We herein report the first iterative synthesis of five inulin-type FOSs with degrees of polymerization ranging from 3 to 7 via highly stereoselective β-(2 → 1)-D-fructofuranosylation on a gram scale. Central to the synthesis is the decisive use of the 1-O-TIPS-6-O-picoloyl-protected fructofuranosyl thioglycoside donor, which assured the excellent β-selective glycosylation by the hydrogen-bond-mediated aglycone delivery (HAD).

The purpose of this paper was to obtain a more in-depth understanding of the influence of migration type rust inhibitor on rust-inhibiting and the performance of concrete.Ten concents of migration type rust inhibitor BE were choosen, the relationship between content of BE with electrochemical impedance was investigated,and the influence of migration type rust inhibitor on rust-inhibiting was analyzed. When the content of rust inhibitor is 2%, the effects of BE on setting time of cement , strength of concrete,and durability of concrete were discussed,The results shows that BE has a great effect on rust-inhibiting;BE has a minor effect on setting time of cement;BE reduces the early strength of concrete,but has no influences on the late strength of concrete;BE can improve the durability of concrete.

This paper studies on the characteristics of strength and deformation of brittle rock under different compression condition by experimental tests. A lot of experimental tests for the Xiangjiaba sandstone are carried out under different compression condition, including uniaxial compression, triaxial compression, uniaxial monocyclic compression and uniaxial loading and unloading. Base on the experimental test results of the Xiangjiaba sandstone, the strength and deformation of brittle rock are analyzed, and some comparative analysis for the mechanics characteristics of brittle rock are carried out. The compute results show that, the peak strength of brittle rock is increased with the confining stress, and close to a linear relationship. Its also show that, the peak strength is not increased under the monocyclic compression, neither for the loading and unloading condition.