Bin2vec: learning representations of binary executable programs for security tasks

Tackling binary program analysis problems has traditionally implied manually defining rules and heuristics, a tedious and time consuming task for human analysts. In order to improve automation and scalability, we propose an alternative direction based on distributed representations of binary programs with applicability to a number of downstream tasks. We introduce Bin2vec, a new approach leveraging Graph Convolutional Networks (GCN) along with computational program graphs in order to learn a high dimensional representation of binary executable programs. We demonstrate the versatility of this approach by using our representations to solve two semantically different binary analysis tasks – functional algorithm classification and vulnerability discovery. We compare the proposed approach to our own strong baseline as well as published results, and demonstrate improvement over state-of-the-art methods for both tasks. We evaluated Bin2vec on 49191 binaries for the functional algorithm classification task, and on 30 different CWE-IDs including at least 100 CVE entries each for the vulnerability discovery task. We set a new state-of-the-art result by reducing the classification error by 40% compared to the source-code based inst2vec approach, while working on binary code. For almost every vulnerability class in our dataset, our prediction accuracy is over 80% (and over 90% in multiple classes).

National projects and government programmes: functional algorithm for evaluating and modelling using the Data Science methodology

Programme and target planning procedures in Russia have a lot of shortcomings, related to the selection of priority goals, establishment of criteria for evaluating the effectiveness of target programmes, as well as achievement of goals, development of a system of performance indicators, and so on. In addition, the problem of the lack of a high-quality theoretical and legislative framework for the transition to budget expenditures planning in accordance with the principles of result-oriented budgeting remains urgent. The purpose of this paper is to develop a functional fuzzy computing algorithm for modelling the evaluation of government programmes using neural networks. As a part of this work, we obtained stable results in the form of creating a neural network that can analyze government projects using a multi-criteria method, taking into account the root-mean-square error, with an accuracy of up to 95%. The analysis criteria cover all effective areas for predicting the correct use of the government projects by implementing them in the government systems.

Different Conventional and Soft Computing MPPT Techniques for Solar PV Systems with High Step-Up Boost Converters: A Comprehensive Analysis

Solar photovoltaic (PV) systems are attracting a huge focus in the current energy scenario. Various maximum power point tracking (MPPT) methods are used in solar PV systems in order to achieve maximum power. In this article, a clear analysis of conventional MPPT techniques such as variable step size perturb and observe (VSS-P&O), modified incremental conductance (MIC), fractional open circuit voltage (FOCV) has been carried out. In addition, the soft computing MPPT techniques such as fixed step size radial basis functional algorithm (FSS-RBFA), variable step size radial basis functional algorithm (VSS-RBFA), adaptive fuzzy logic controller (AFLC), particle swarm optimization (PSO), and cuckoo search (CS) MPPT techniques are presented along with their comparative analysis. The comparative analysis is done under static and dynamic irradiation conditions by considering algorithm complexity, tracking speed, oscillations at MPP, and sensing parameters. The single-diode model PV panel and double-diode model PV panel are also compared in terms of fill factor (FF) and maximum power extraction. Clear insight is presented supporting the suitability of MPPT techniques for different types of converter configurations.

Shallow Landslide Prediction Using a Novel Hybrid Functional Machine Learning Algorithm

We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in the Sarkhoon watershed, Iran. We developed a new ensemble model which is a combination of a functional algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD model to predict the landslides. The model incorporates 20 landslide conditioning factors, which we ranked using the least-square support vector machine (LSSVM) technique. For the modeling, we considered 98 landslide locations, of which 70% (79) were used for training and 30% (19) for validation processes. Model validation was performed using sensitivity, specificity, accuracy, the root mean square error (RMSE) and the area under the receiver operatic characteristic (AUC) curve. We also used soft computing benchmark models, including SGD, logistic regression (LR), logistic model tree (LMT) and functional tree (FT) algorithms for model validation and comparison. The selected conditioning factors were significant in landslide occurrence but distance to road was found to be the most important factor. The ABSGD model (AUC= 0.860) outperformed the LR (0.797), SGD (0.776), LMT (0.740) and FT (0.734) models. Our results confirm that the combined use of a functional algorithm and a Meta classifier prevents over-fitting, reduces noise and enhances the power prediction of the individual SGD algorithm for the spatial prediction of landslides.