• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.3
• /
• pp.127-132
• /
• 2018

In this paper, a scheme for the evaluation of variability in the eigen-modes of functionally graded material(FGM) beams is proposed within the framework of perturbation-based stochastic analysis. As a random parameter, the spatially varying elastic modulus of FGM along the axial direction at the mid-surface of the beam is chosen, and the thru-thickness variation of the elastic modulus is assumed to follow the original form of exponential variation. In deriving the formulation, the first order Taylor expansion on the eigen-modes is employed. As an example, a simply supported FGM beam having symmetric elastic modulus with respect to the mid-surface is chosen. Monte Carlo analysis is also performed to check if the proposed scheme gives reasonable outcomes. From the analyses it is found that the two schemes give almost identical results of the mean and standard deviation of eigen-modes. With the propose scheme, the standard deviation shape of respective eigen-modes can be evaluated easily. The deviated mode shape is found to have one more zero-slope points than the mother modes shapes, irrespective of order of modes. The amount of deviation from the mean is found to have larger values for the higher modes than the lower modes.

• Journal of the Korean earth science society
• /
• v.22 no.6
• /
• pp.512-527
• /
• 2001

Separated flows passed complex geometries are modeled by discrete vortex techniques. The flows are assumed to be rotational and inviscid, and a new techlnique is described to determine the stream functions for linear shear profiles. The geometries considered are the snow cornice and the backward-facing step, whose edges allow for the separation of the flow and reattachment downstream of the recirculation regions. A point vortex has been added to the flows in order to constrain the separation points to be located at the edges, while the conformal mappings have been modified in order to smooth the sharp edges and to let the separation points free to oscillate around the points of maximum curvature. Unsteadiness is imposed to the flow by perturbing the vortex location, either by displacing the vortex from the equilibrium, or by imposing a random perturbation with zero mean to the vortex in equilibrium. The trajectories of passive scalars continuously released upwind of the separation point and trapped by the recirculating bubble are numerically integrated, and concentration time series are calculated at fixed locations downwind of the reattachment points. This model proves to be capable of reproducing the trapping and intermittent release of scalars, in agreement with the simulation of the flow passed a snow cornice performed by a discrete multi-vortex model, as well as with direct numerical simulations of the flow passed a backward-facing step. The results of simulation indicate that for flows undergoing separation and reattachment the unsteadiness of the recirculating bubble is the main mechanism responsible for the intense large-scale concentration fluctuations downstream.

• Journal of Korean Society of Steel Construction
• /
• v.20 no.1
• /
• pp.21-31
• /
• 2008

response surface method (RSM) is widely used to evaluate th e extremely smal probability of ocurence or toanalyze the reliability of very complicated structures. Althoug h Monte-Carlo Simulation (MCS) technique can evaluate any system, the procesing time of MCS dependson the reciprocal num ber of the probability of failure. The stochastic finite element method could solve thislimitation. However, it is limit ed to the specific program, in which the mean and coeficient o f random variables are programed by a perturbation or by a weigh ted integral method. Therefore, it is not aplicable when erequisite programing. In a few number of stage analyses, RSM can construct a regresion model from the response of the c omplicated structural system, thus, saving time and efort significantly. However, the acuracy of RSM depends on the dist ance of the axial points and on the linearity of the limit stat e functions. To improve the convergence in exact solution regardl es of the linearity limit of state functions, an improved adaptive response surface method is developed. The analyzed res ults have ben verified using linear and quadratic forms of response surface functions in two examples. As a result, the be st combination of the improved RSM techniques is determined and programed in a numerical code. The developed linear adapti ve weighted response surface method (LAW-RSM) shows the closest converged reliability indices, compared with quadratic form or non-adaptive or non-weighted RSMs.