Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Increasing numbers of software vulnerabilities are discovered every year whether they are reported publicly or discovered internally in proprietary code. These vulnerabilities can pose serious risk of exploit and result in system compromise, information leaks, or denial of service. We leveraged the wealth of C and C++ open-source code available to develop a large-scale function-level vulnerability detection system using machine learning. To supplement existing labeled vulnerability datasets, we compiled a vast dataset of millions of open-source functions and labeled it with carefully-selected findings from three different static analyzers that indicate potential exploits. The labeled dataset is available at: this https URL. Using these datasets, we developed a fast and scalable vulnerability detection tool based on deep feature representation learning that directly interprets lexed source code. We evaluated our tool on code from both real software packages and the NIST SATE IV benchmark dataset. Our results demonstrate that deep feature representation learning on source code is a promising approach for automated software vulnerability detection.

Automated Vulnerability Detection in Source Code Using Deep Representation Learning

Introduction.- Regularization Theory and Recent Developments.- Nonstandard Regularization and Advanced Optimization Theory and Methods.- Numerical Inversion in Geoscience and Quantitative Remote Sensing.

Optimization and regularization for computational inverse problems and applications

There are some quasi-tridiagonal system of linear equations arising from numerical simulations, and some solving algorithms encounter great challenge on solving quasi-tridiagonal system of linear equations with more than millions of dimensions as the scale of problems increases. We present a solving method which mixes direct and iterative methods, and our method needs less storage space in a computing process. A quasi-tridiagonal matrix is split into a tridiagonal matrix and a sparse matrix using our method and then the tridiagonal equation can be solved by the direct methods in the iteration processes. Because the approximate solutions obtained by the direct methods are closer to the exact solutions, the convergence speed of solving the quasi-tridiagonal system of linear equations can be improved. Furthermore, we present an improved cyclic reduction algorithm using a partition strategy to solve tridiagonal equations on GPU, and the intermediate data in computing are stored in shared memory so as to significantly reduce the latency of memory access. According to our experiments on 10 test cases, the average number of iterations is reduced significantly by using our method compared with Jacobi, GS, GMRES, and BiCG respectively, and close to those of BiCGSTAB, BiCRSTAB, and TFQMR. For parallel mode, the parallel computing efficiency of our method is raised by partition strategy, and the performance using our method is better than those of the commonly used iterative and direct methods because of less amount of calculation in an iteration.

A Hybrid Parallel Solving Algorithm on GPU for Quasi-Tridiagonal System of Linear Equations

https://www.icl.utk.edu/files/publications/2013/icl-utk-633-2013.pdf

Soft Error Resilient QR Factorization for Hybrid System with GPGPU

Defect prediction is one of the key challenges in software development and programming language research for improving software quality and reliability The problem in this area is to properly identify the defective source code with high accuracy Developing a fault prediction model is a challenging problem, and many approaches have been proposed throughout history The recent breakthrough in machine learning technologies, especially the development of deep learning techniques, has led to many problems being solved by these methods Our survey focuses on the deep learning techniques for defect prediction We analyse the recent works on the topic, study the methods for automatic learning of the semantic and structural features from the code, discuss the open problems and present the recent trends in the field

A Survey on Software Defect Prediction Using Deep Learning

We describe the parallel algorithms for studying the structural features of the anomalies in the gravity and magnetic fields of the lithosphere, which are based on the height transformations of the data. The algorithms are numerically implemented on the Uran supercomputer. The suggested computer technology is used for constructing the maps of the regional and local anomalies of the magnetic and gravity fields for the northeastern sector of Europe within an area confined between 48°–62° E and 60°–68° N.

Studying the structural features of the lithospheric magnetic and gravity fields with the use of parallel algorithms

Parallel algorithms for solving linear systems with block-tridiagonal matrices on multi-core CPU with GPU

An algorithm for modeling the evolution of a monodispersed ensemble of precipitates of a variable composition during heat treatment has been developed. In this algorithm, we for the first time have simultaneously taken into consideration the effect of diffusion processes in particles on their evolution kinetics, as well as the multicomponent nature of the alloy, and diffusion interaction between the components. The proposed method is based on the simultaneous solution of a set of diffusion equations and the balance and thermodynamic equations. A qualitative comparison of the results of calculations of the variation of the carbonitride-precipitate composition over the depth of precipitates upon heat treatment with available experimental data has been performed.

Computer simulation of the diffusion interaction between carbonitride precipitates and austenitic matrix with allowance for the possibility of variation of their composition

/pdf/algorithms-for-solving-the-structural-gravity-problem-in-a-pz9kvtkglf.pdf

Elena N. Akimova

Papers

A Survey on Software Defect Prediction Using Deep Learning

Studying the structural features of the lithospheric magnetic and gravity fields with the use of parallel algorithms

Parallel algorithms for solving linear systems with block-tridiagonal matrices on multi-core CPU with GPU

Computer simulation of the diffusion interaction between carbonitride precipitates and austenitic matrix with allowance for the possibility of variation of their composition

Algorithms for solving the structural gravity problem in a multilayer medium