Smart Contract Vulnerability Detection Model Based on Multi-Task Learning.

The key issue in the field of smart contract security is efficient and rapid vulnerability detection in smart contracts. Most of the existing detection methods can only detect the presence of vulnerabilities in the contract and can hardly identify their type. Furthermore, they have poor scalability. To resolve these issues, in this study, we developed a smart contract vulnerability detection model based on multi-task learning. By setting auxiliary tasks to learn more directional vulnerability features, the detection capability of the model was improved to realize the detection and recognition of vulnerabilities. The model is based on a hard-sharing design, which consists of two parts. First, the bottom sharing layer is mainly used to learn the semantic information of the input contract. The text representation is first transformed into a new vector by word and positional embedding, and then the neural network, based on an attention mechanism, is used to learn and extract the feature vector of the contract. Second, the task-specific layer is mainly employed to realize the functions of each task. A classical convolutional neural network was used to construct a classification model for each task that learns and extracts features from the shared layer for training to achieve their respective task objectives. The experimental results show that the model can better identify the types of vulnerabilities after adding the auxiliary vulnerability detection task. This model realizes the detection of vulnerabilities and recognizes three types of vulnerabilities. The multi-task model was observed to perform better and is less expensive than a single-task model in terms of time, computation, and storage.

Connected function of PRAF/RLD and GNOM in membrane trafficking controls intrinsic cell polarity in plants.

Cell polarity is a fundamental feature underlying cell morphogenesis and organismal development. In the Arabidopsis stomatal lineage, the polarity protein BASL controls stomatal asymmetric cell division. However, the cellular machinery by which this intrinsic polarity site is established remains unknown. Here, we identify the PRAF/RLD proteins as BASL physical partners and mutating four PRAF members leads to defects in BASL polarization. Members of PRAF proteins are polarized in stomatal lineage cells in a BASL-dependent manner. Developmental defects of the praf mutants phenocopy those of the gnom mutants. GNOM is an activator of the conserved Arf GTPases and plays important roles in membrane trafficking. We further find PRAF physically interacts with GNOM in vitro and in vivo. Thus, we propose that the positive feedback of BASL and PRAF at the plasma membrane and the connected function of PRAF and GNOM in endosomal trafficking establish intrinsic cell polarity in the Arabidopsis stomatal lineage.

Enhanced Microwave Absorption and Surface Wave Attenuation Properties of Co0.5Ni0.5Fe2O4 Fibers/Reduced Graphene Oxide Composites.

Co0.5Ni0.5Fe2O4 fibers with a diameter of about 270 nm and a length of about 10 µm were synthesized by a microemulsion-mediated solvothermal method with subsequent heat treatment. The Co0.5Ni0.5Fe2O4 fibers/reduced graphene oxide (RGO) composite was prepared by a facile in-situ chemical reduction method. The crystalline structures and morphologies were investigated based on X-ray diffraction patterns and scanning electron microscopy. Magnetization measurements were carried out using a vibrating sample magnetometer at room temperature. Co0.5Ni0.5Fe2O4 fibers/RGO composites achieve both a wider and stronger absorption and an adjustable surface wave attenuation compared with Co0.5Ni0.5Fe2O4 fibers, indicating the potential for application as advanced microwave absorbers.