Готові списки джерел за темами / Fast Gradient Sign Method

Добірка наукової літератури з теми "Fast Gradient Sign Method"

Автор: Grafiati

Опубліковано: 6 вересня 2023

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Зміст

Статті в журналах
Дисертації
Книги
Частини книг
Тези доповідей конференцій
Звіти організацій

Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Fast Gradient Sign Method".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Статті в журналах з теми "Fast Gradient Sign Method"

Zou, Junhua, Yexin Duan, Boyu Li, Wu Zhang, Yu Pan, and Zhisong Pan. "Making Adversarial Examples More Transferable and Indistinguishable." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 3 (June 28, 2022): 3662–70. http://dx.doi.org/10.1609/aaai.v36i3.20279.

Повний текст джерела

Анотація:

Fast gradient sign attack series are popular methods that are used to generate adversarial examples. However, most of the approaches based on fast gradient sign attack series cannot balance the indistinguishability and transferability due to the limitations of the basic sign structure. To address this problem, we propose a method, called Adam Iterative Fast Gradient Tanh Method (AI-FGTM), to generate indistinguishable adversarial examples with high transferability. Besides, smaller kernels and dynamic step size are also applied to generate adversarial examples for further increasing the attack success rates. Extensive experiments on an ImageNet-compatible dataset show that our method generates more indistinguishable adversarial examples and achieves higher attack success rates without extra running time and resource. Our best transfer-based attack NI-TI-DI-AITM can fool six classic defense models with an average success rate of 89.3% and three advanced defense models with an average success rate of 82.7%, which are higher than the state-of-the-art gradient-based attacks. Additionally, our method can also reduce nearly 20% mean perturbation. We expect that our method will serve as a new baseline for generating adversarial examples with better transferability and indistinguishability.

Стилі APA, Harvard, Vancouver, ISO та ін.

Wibawa, Sigit. "Analysis of Adversarial Attacks on AI-based With Fast Gradient Sign Method." International Journal of Engineering Continuity 2, no. 2 (August 1, 2023): 72–79. http://dx.doi.org/10.58291/ijec.v2i2.120.

Повний текст джерела

Анотація:

Artificial intelligence (AI) has become a key driving force in sectors from transportation to healthcare, and is opening up tremendous opportunities for technological advancement. However, behind this promising potential, AI also presents serious security challenges. This article aims to investigate attacks on AI and security challenges that must be faced in the era of artificial intelligence, this research aims to simulate and test the security of AI systems due to adversarial attacks. We can use the Python programming language for this, using several libraries and tools. One that is very popular for testing the security of AI models is CleverHans, and by understanding those threats we can protect the positive developments of AI in the future. this research provides a thorough understanding of attacks in AI technology especially in neural networks and machine learning, and the security challenge we face is that adding a little interference to the input data causes the AI model to produce wrong predictions in adversarial attacks there is the FGSM model which with an epsilon value of 0.1 causes the model suffered a drastic reduction in accuracy of around 66%, which means that the attack managed to mislead the model and lead to incorrect predictions. in the future understanding this threat is the key to protecting the positive development of AI. With a thorough understanding of AI attacks and the security challenges we address, we can build a solid foundation to effectively address these threats.

Стилі APA, Harvard, Vancouver, ISO та ін.

Sun, Guangling, Yuying Su, Chuan Qin, Wenbo Xu, Xiaofeng Lu, and Andrzej Ceglowski. "Complete Defense Framework to Protect Deep Neural Networks against Adversarial Examples." Mathematical Problems in Engineering 2020 (May 11, 2020): 1–17. http://dx.doi.org/10.1155/2020/8319249.

Повний текст джерела

Анотація:

Although Deep Neural Networks (DNNs) have achieved great success on various applications, investigations have increasingly shown DNNs to be highly vulnerable when adversarial examples are used as input. Here, we present a comprehensive defense framework to protect DNNs against adversarial examples. First, we present statistical and minor alteration detectors to filter out adversarial examples contaminated by noticeable and unnoticeable perturbations, respectively. Then, we ensemble the detectors, a deep Residual Generative Network (ResGN), and an adversarially trained targeted network, to construct a complete defense framework. In this framework, the ResGN is our previously proposed network which is used to remove adversarial perturbations, and the adversarially trained targeted network is a network that is learned through adversarial training. Specifically, once the detectors determine an input example to be adversarial, it is cleaned by ResGN and then classified by the adversarially trained targeted network; otherwise, it is directly classified by this network. We empirically evaluate the proposed complete defense on ImageNet dataset. The results confirm the robustness against current representative attacking methods including fast gradient sign method, randomized fast gradient sign method, basic iterative method, universal adversarial perturbations, DeepFool method, and Carlini & Wagner method.

Стилі APA, Harvard, Vancouver, ISO та ін.

Kim, Hoki, Woojin Lee, and Jaewook Lee. "Understanding Catastrophic Overfitting in Single-step Adversarial Training." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 9 (May 18, 2021): 8119–27. http://dx.doi.org/10.1609/aaai.v35i9.16989.

Повний текст джерела

Анотація:

Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the robust accuracy against projected gradient descent (PGD) suddenly decreases to 0% after a few epochs, whereas the robust accuracy against fast gradient sign method (FGSM) increases to 100%. In this paper, we demonstrate that catastrophic overfitting is very closely related to the characteristic of single-step adversarial training which uses only adversarial examples with the maximum perturbation, and not all adversarial examples in the adversarial direction, which leads to decision boundary distortion and a highly curved loss surface. Based on this observation, we propose a simple method that not only prevents catastrophic overfitting, but also overrides the belief that it is difficult to prevent multi-step adversarial attacks with single-step adversarial training.

Стилі APA, Harvard, Vancouver, ISO та ін.

Saxena, Rishabh, Amit Sanjay Adate, and Don Sasikumar. "A Comparative Study on Adversarial Noise Generation for Single Image Classification." International Journal of Intelligent Information Technologies 16, no. 1 (January 2020): 75–87. http://dx.doi.org/10.4018/ijiit.2020010105.

Повний текст джерела

Анотація:

With the rise of neural network-based classifiers, it is evident that these algorithms are here to stay. Even though various algorithms have been developed, these classifiers still remain vulnerable to misclassification attacks. This article outlines a new noise layer attack based on adversarial learning and compares the proposed method to other such attacking methodologies like Fast Gradient Sign Method, Jacobian-Based Saliency Map Algorithm and DeepFool. This work deals with comparing these algorithms for the use case of single image classification and provides a detailed analysis of how each algorithm compares to each other.

Стилі APA, Harvard, Vancouver, ISO та ін.

Yang, Bo, Kaiyong Xu, Hengjun Wang, and Hengwei Zhang. "Random Transformation of image brightness for adversarial attack." Journal of Intelligent & Fuzzy Systems 42, no. 3 (February 2, 2022): 1693–704. http://dx.doi.org/10.3233/jifs-211157.

Повний текст джерела

Анотація:

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before DNNs are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications. However, under the challenging black-box setting, the attack success rate, i.e., the transferability of adversarial examples, still needs to be improved. Based on image augmentation methods, this paper found that random transformation of image brightness can eliminate overfitting in the generation of adversarial examples and improve their transferability. In light of this phenomenon, this paper proposes an adversarial example generation method, which can be integrated with Fast Gradient Sign Method (FGSM)-related methods to build a more robust gradient-based attack and to generate adversarial examples with better transferability. Extensive experiments on the ImageNet dataset have demonstrated the effectiveness of the aforementioned method. Whether on normally or adversarially trained networks, our method has a higher success rate for black-box attacks than other attack methods based on data augmentation. It is hoped that this method can help evaluate and improve the robustness of models.

Стилі APA, Harvard, Vancouver, ISO та ін.

Trinh Quang Kien. "Improving the robustness of binarized neural network using the EFAT method." Journal of Military Science and Technology, CSCE5 (December 15, 2021): 14–23. http://dx.doi.org/10.54939/1859-1043.j.mst.csce5.2021.14-23.

Повний текст джерела

Анотація:

In recent years with the explosion of research in artificial intelligence, deep learning models based on convolutional neural networks (CNNs) are one of the promising architectures for practical applications thanks to their reasonably good achievable accuracy. However, CNNs characterized by convolutional layers often have a large number of parameters and computational workload, leading to large energy consumption for training and network inference. The binarized neural network (BNN) model has been recently proposed to overcome that drawback. The BNNs use binary representation for the inputs and weights, which inherently reduces memory requirements and simplifies computations while still maintaining acceptable accuracy. BNN thereby is very suited for the practical realization of Edge-AI application on resource- and energy-constrained devices such as embedded or mobile devices. As CNN and BNN both compose linear transformations layers, they can be fooled by adversarial attack patterns. This topic has been actively studied recently but most of them are for CNN. In this work, we examine the impact of the adversarial attack on BNNs and propose a solution to improve the accuracy of BNN against this type of attack. Specifically, we use an Enhanced Fast Adversarial Training (EFAT) method to train the network that helps the BNN be more robust against major adversarial attack models with a very short training time. Experimental results with Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attack models on our trained BNN network with MNIST dataset increased accuracy from 31.34% and 0.18% to 96.96% and 85.08%, respectively.

Стилі APA, Harvard, Vancouver, ISO та ін.

Hirano, Hokuto, and Kazuhiro Takemoto. "Simple Iterative Method for Generating Targeted Universal Adversarial Perturbations." Algorithms 13, no. 11 (October 22, 2020): 268. http://dx.doi.org/10.3390/a13110268.

Повний текст джерела

Анотація:

Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, a single perturbation known as the universal adversarial perturbation (UAP) can foil most classification tasks conducted by DNNs. Thus, different methods for generating UAPs are required to fully evaluate the vulnerability of DNNs. A realistic evaluation would be with cases that consider targeted attacks; wherein the generated UAP causes the DNN to classify an input into a specific class. However, the development of UAPs for targeted attacks has largely fallen behind that of UAPs for non-targeted attacks. Therefore, we propose a simple iterative method to generate UAPs for targeted attacks. Our method combines the simple iterative method for generating non-targeted UAPs and the fast gradient sign method for generating a targeted adversarial perturbation for an input. We applied the proposed method to state-of-the-art DNN models for image classification and proved the existence of almost imperceptible UAPs for targeted attacks; further, we demonstrated that such UAPs can be easily generated.

Стилі APA, Harvard, Vancouver, ISO та ін.

An, Tong, Tao Zhang, Yanzhang Geng, and Haiquan Jiao. "Normalized Combinations of Proportionate Affine Projection Sign Subband Adaptive Filter." Scientific Programming 2021 (August 26, 2021): 1–12. http://dx.doi.org/10.1155/2021/8826868.

Повний текст джерела

Анотація:

The proportionate affine projection sign subband adaptive filter (PAP-SSAF) has a better performance than the affine projection sign subband adaptive filter (AP-SSAF) when we eliminate the echoes. Still, the robustness of the PAP-SSAF algorithm is insufficient under unknown environmental conditions. Besides, the best balance remains to be found between low steady-state misalignment and fast convergence rate. In order to solve this problem, we propose a normalized combination of PAP-SSAF (NCPAP-SSAF) based on the normalized adaption schema. In this paper, a power normalization adaptive rule for mixing parameters is proposed to further improve the performance of the NCPAP-SSAF algorithm. By using Nesterov’s accelerated gradient (NAG) method, the mixing parameter of the control combination can be obtained with less time consumed when we take the l1-norm of the subband error as the cost function. We also test the algorithmic complexity and memory requirements to illustrate the rationality of our method. In brief, our study contributes a novel adaptive filter algorithm, accelerating the convergence speed, reducing the steady-state error, and improving the robustness. Thus, the proposed method can be utilized to improve the performance of echo cancellation. We will optimize the combination structure and simplify unnecessary calculations to reduce the algorithm’s computational complexity in future research.

Стилі APA, Harvard, Vancouver, ISO та ін.

Kadhim, Ansam, and Salah Al-Darraji. "Face Recognition System Against Adversarial Attack Using Convolutional Neural Network." Iraqi Journal for Electrical and Electronic Engineering 18, no. 1 (November 6, 2021): 1–8. http://dx.doi.org/10.37917/ijeee.18.1.1.

Повний текст джерела

Анотація:

Face recognition is the technology that verifies or recognizes faces from images, videos, or real-time streams. It can be used in security or employee attendance systems. Face recognition systems may encounter some attacks that reduce their ability to recognize faces properly. So, many noisy images mixed with original ones lead to confusion in the results. Various attacks that exploit this weakness affect the face recognition systems such as Fast Gradient Sign Method (FGSM), Deep Fool, and Projected Gradient Descent (PGD). This paper proposes a method to protect the face recognition system against these attacks by distorting images through different attacks, then training the recognition deep network model, specifically Convolutional Neural Network (CNN), using the original and distorted images. Diverse experiments have been conducted using combinations of original and distorted images to test the effectiveness of the system. The system showed an accuracy of 93% using FGSM attack, 97% using deep fool, and 95% using PGD.

Стилі APA, Harvard, Vancouver, ISO та ін.

Більше джерел

Дисертації з теми "Fast Gradient Sign Method"

Zhang, Zichen. "Local gradient estimate for porous medium and fast diffusion equations by Martingale method." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:551f79f8-b309-4a1f-8afa-c7dc433dad82.

Повний текст джерела

Анотація:

This thesis focuses on a certain type of nonlinear parabolic partial differential equations, i.e. PME and FDE. Chapter 1 consists of a survey on results related to PME and FDE, and a short review on some works about deriving gradient estimates in probabilistic ways. In Chapter 2 we estimate gradient on space variables of solutions to the heat equation on Euclidean space. The main idea is to construct two semimartingales by letting the solution and its gradient running backward on the path space of a diffusion process. Estimates derived from decompositions of those two semimartingales are then combined to give rise to an upper bound on gradient that only involves the maximum of the initial data and time variable. In particular, it is independent of the dimension. In Chapter 3 we carry the idea in Chapter 2 onto the study of positive solutions to PME or FDE, and obtained a similar type of bound on |∇u| for local solutions to PME or FDE on Euclidean space. In existing literature there have always been constraints on m. By considering a more general form of transformation on u and introducing a family of equivalent measures on path space, we add more flexibility to our method. Thus our result is valid for a larger range of m. For global solutions, when m violates our constraint, we need two-sided bound on u to control |∇u|. In Chapter 4 we utilize maximum principle to derive Li-Yau type gradient estimate for PME on a compact Riemannian manifold with Ricci curvature bounded from below. Our result is able to yield a Harnack inequality possessing the right order in time variable when the lower bound of Ricci curvature is negative.

Стилі APA, Harvard, Vancouver, ISO та ін.

Pester, M., and S. Rjasanow. "A parallel version of the preconditioned conjugate gradient method for boundary element equations." Universitätsbibliothek Chemnitz, 1998. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-199800455.

Повний текст джерела

Анотація:

The parallel version of precondition techniques is developed for matrices arising from the Galerkin boundary element method for two-dimensional domains with Dirichlet boundary conditions. Results were obtained for implementations on a transputer network as well as on an nCUBE-2 parallel computer showing that iterative solution methods are very well suited for a MIMD computer. A comparison of numerical results for iterative and direct solution methods is presented and underlines the superiority of iterative methods for large systems.

Стилі APA, Harvard, Vancouver, ISO та ін.

Strauss, Arne Karsten. "Numerical Analysis of Jump-Diffusion Models for Option Pricing." Thesis, Virginia Tech, 2006. http://hdl.handle.net/10919/33917.

Повний текст джерела

Анотація:

Jump-diffusion models can under certain assumptions be expressed as partial integro-differential equations (PIDE). Such a PIDE typically involves a convection term and a nonlocal integral like for the here considered models of Merton and Kou. We transform the PIDE to eliminate the convection term, discretize it implicitly using finite differences and the second order backward difference formula (BDF2) on a uniform grid. The arising dense linear system is solved by an iterative method, either a splitting technique or a circulant preconditioned conjugate gradient method. Exploiting the Fast Fourier Transform (FFT) yields the solution in only $O(n\log n)$ operations and just some vectors need to be stored. Second order accuracy is obtained on the whole computational domain for Merton's model whereas for Kou's model first order is obtained on the whole computational domain and second order locally around the strike price. The solution for the PIDE with convection term can oscillate in a neighborhood of the strike price depending on the choice of parameters, whereas the solution obtained from the transformed problem is stabilized.
Master of Science

Стилі APA, Harvard, Vancouver, ISO та ін.

Alli-Oke, Razak Olusegun. "Robustness and optimization in anti-windup control." Thesis, University of Manchester, 2014. https://www.research.manchester.ac.uk/portal/en/theses/robustness-and-optimization-in-antiwindup-control(8b98c920-90c3-4fbc-95a8-0cc7ae2a607a).html.

Повний текст джерела

Анотація:

This thesis is broadly concerned with online-optimizing anti-windup control. These are control structures that implement some online-optimization routines to compensate for the windup effects in constrained control systems. The first part of this thesis examines a general framework for analyzing robust preservation in anti-windup control systems. This framework - the robust Kalman conjecture - is defined for the robust Lur’e problem. This part of the thesis verifies this conjecture for first-order plants perturbed by various norm-bounded unstructured uncertainties. Integral quadratic constraint theory is exploited to classify the appropriate stability multipliers required for verification in these cases. The remaining part of the thesis focusses on accelerated gradient methods. In particular, tight complexity-certificates can be obtained for the Nesterov gradient method, which makes it attractive for implementation of online-optimizing anti-windup control. This part of the thesis presents a proposed algorithm that extends the classical Nesterov gradient method by using available secant information. Numerical results demonstrating the efficiency of the proposed algorithm are analysed with the aid of performance profiles. As the objective function becomes more ill-conditioned, the proposed algorithm becomes significantly more efficient than the classical Nesterov gradient method. The improved performance bodes well for online-optimization anti-windup control since ill-conditioning is common place in constrained control systems. In addition, this thesis explores another subcategory of accelerated gradient methods known as Barzilai-Borwein gradient methods. Here, two algorithms that modify the Barzilai-Borwein gradient method are proposed. Global convergence of the proposed algorithms for all convex functions is established by using discrete Lyapunov theorems.

Стилі APA, Harvard, Vancouver, ISO та ін.

Vivek, B. S. "Towards Learning Adversarially Robust Deep Learning Models." Thesis, 2019. https://etd.iisc.ac.in/handle/2005/4488.

Повний текст джерела

Анотація:

Deep learning models have shown impressive performance across a wide spectrum of computer vision applications, including medical diagnosis and autonomous driving. One of the major concerns that these models face is their susceptibility to adversarial samples: samples with small, crafted noise designed to manipulate the model’s prediction. A defense mechanism named Adversarial Training (AT) shows promising results against these attacks. This training regime augments mini-batches with adversaries. However, to scale this training to large networks and datasets, fast and simple methods (e.g., single-step methods such as Fast Gradient Sign Method (FGSM)), are essential for generating these adversaries. But, single-step adversarial training (e.g., FGSM adversarial training) converges to a degenerate minimum, where the model merely appears to be robust. As a result, models are vulnerable to simple black-box attacks. In this thesis, we explore the following aspects of adversarial training: Failure of Single-step Adversarial Training: In the first part of the thesis, we will demonstrate that the pseudo robustness of an adversarially trained model is due to the limitations in the existing evaluation procedure. Further, we introduce novel variants of white-box and black-box attacks, dubbed “gray-box adversarial attacks”, based on which we propose a novel evaluation method to assess the robustness of the learned models. A novel variant of adversarial training named “Gray-box Adversarial Training” that uses intermediate versions of the model to seed the adversaries is proposed to improve the model’s robustness. Regularizers for Single-step Adversarial Training: In this part of the thesis, we will discuss various regularizers that could help to learn robust models using single-step adversarial training methods. (i) Regularizer that enforces logits for FGSM and I-FGSM (iterative-FGSM) of a clean sample, to be similar (imposed on only one pair of an adversarial sample in a mini-batch), (ii) Regularizer that enforces logits for FGSM and R-FGSM (Random+FGSM) of a clean sample, to be similar, (iii) Monotonic loss constraint: Enforces the loss to increase monotonically with an increase in the perturbation size of the FGSM attack, and (iv) Dropout with decaying dropout probability: Introduces dropout layer with decaying dropout probability, after each nonlinear layer of a network. Incorporating Domain Knowledge to Improve Model’s Adversarial Robustness: In this final part of the thesis, we show that the existing normal training method fails to incorporate domain knowledge into the learned feature representation of the network. Further, we show that incorporating domain knowledge into the learned feature representation of the network results in a significant improvement in the robustness of the network against adversarial attacks, within normal training regime.

Стилі APA, Harvard, Vancouver, ISO та ін.

Juan, Yu-Chin, and 阮毓欽. "A Fast Parallel Stochastic Gradient Method for Matrix Factorization in Shared Memory Systems." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/32077403329819649481.

Повний текст джерела

Анотація:

碩士
國立臺灣大學
資訊工程學研究所
102
Matrix factorization is known to be an effective method for recommender systems that are given only the ratings from users to items. Currently, stochastic gradient (SG) method is one of the most popular algorithms for matrix factorization. However, as a sequential approach, SG is difficult to be parallelized for handling web-scale problems. In this thesis, we develop a fast parallel SG method, FPSG, for shared memory systems. By dramatically reducing the cache-miss rate and carefully addressing the load balance of threads, FPSG is more efficient than state-of-the-art parallel algorithms for matrix factorization.

Стилі APA, Harvard, Vancouver, ISO та ін.

WANG, CHIH-HAO, and 王志豪. "Solving Scattering Problems of Large-Sized Conducting Objects by Conjugate Gradient Algorithm with Fast Multipole Method." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/39689963107809382071.

Повний текст джерела

Анотація:

碩士
國立海洋大學
電機工程學系
89
In this thesis, we use the method of moment (MoM) to solve the electromagnetic scattering problems. A three-dimension arbitrary-shaped conductive object is divided into triangular patches, and the integral equation is discretized by MoM. Then a conjugate gradient method (CGM) is used to iteratively solve the resulting matrix equation for unknown expansion coefficients for the surface current. But when the number of unknowns is large, the CGM takes more time at each iteration. In view of this, we use the fast multipole method (FMM) to speed up the matrix-vector multiply in the CGM. The FMM reduces the complexity of a matrix-vector multiply from to , where N is the number of unknowns. The program makes use of the object-oriented programming technique and uses visual C++ as a tool to design some practical classes, which are convenient to expand programs further. This FMM algorithm also requires less memory, and hence, large and more practical problems can be solved on a PC computer.

Стилі APA, Harvard, Vancouver, ISO та ін.

Yu, Zhiru. "A CG-FFT Based Fast Full Wave Imaging Method and its Potential Industrial Applications." Diss., 2015. http://hdl.handle.net/10161/11344.

Повний текст джерела

Анотація:

This dissertation focuses on a FFT based forward EM solver and its application in inverse problems. The main contributions of this work are two folded. On the one hand, it presents the first scaled lab experiment system in the oil and gas industry for through casing hydraulic fracture evaluation. This system is established to validate the feasibility of contrasts enhanced fractures evaluation. On the other hand, this work proposes a FFT based VIE solver for hydraulic fracture evaluation. This efficient solver is needed for numerical analysis of such problem. The solver is then generalized to accommodate scattering simulations for anisotropic inhomogeneous magnetodielectric objects. The inverse problem on anisotropic objects are also studied.

Before going into details of specific applications, some background knowledge is presented. This dissertation starts with an introduction to inverse problems. Then algorithms for forward and inverse problems are discussed. The discussion on forward problem focuses on the VIE formulation and a frequency domain solver. Discussion on inverse problems focuses on iterative methods.

The rest of the dissertation is organized by the two categories of inverse problems, namely the inverse source problem and the inverse scattering problem.

The inverse source problem is studied via an application in microelectronics. In this application, a FFT based inverse source solver is applied to process near field data obtained by near field scanners. Examples show that, with the help of this inverse source solver, the resolution of unknown current source images on a device under test is greatly improved. Due to the improvement in resolution, more flexibility is given to the near field scan system.

Both the forward and inverse solver for inverse scattering problems are studied in detail. As a forward solver for inverse scattering problems, a fast FFT based method for solving VIE of magnetodielectric objects with large electromagnetic contrasts are presented due to the increasing interest in contrasts enhanced full wave EM imaging. This newly developed VIE solver assigns different basis functions of different orders to expand flux densities and vector potentials. Thus, it is called the mixed ordered BCGS-FFT method. The mixed order BCGS-FFT method maintains benefits of high order basis functions for VIE while keeping correct boundary conditions for flux densities and vector potentials. Examples show that this method has an excellent performance on both isotropic and anisotropic objects with high contrasts. Examples also verify that this method is valid in both high and low frequencies. Based on the mixed order BCGS-FFT method, an inverse scattering solver for anisotropic objects is studied. The inverse solver is formulated and solved by the variational born iterative method. An example given in this section shows a successful inversion on an anisotropic magnetodielectric object.

Finally, a lab scale hydraulic fractures evaluation system for oil/gas reservoir based on previous discussed inverse solver is presented. This system has been setup to verify the numerical results obtained from previously described inverse solvers. These scaled experiments verify the accuracy of the forward solver as well as the performance of the inverse solver. Examples show that the inverse scattering model is able to evaluate contrasts enhanced hydraulic fractures in a shale formation. Furthermore, this system, for the first time in the oil and gas industry, verifies that hydraulic fractures can be imaged through a metallic casing.

Dissertation

Стилі APA, Harvard, Vancouver, ISO та ін.

Книги з теми "Fast Gradient Sign Method"

Pan, Victor. A fast, preconditioned conjugate gradient Toeplitz solver. [Moffett Field, Calif.]: Research Institute for Advanced Computer Science, NASA Ames Research Center, 1989.

Знайти повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Evtushenko, Yury, Vladimir Zubov, and Anna Albu. Optimal control of thermal processes with phase transitions. LCC MAKS Press, 2021. http://dx.doi.org/10.29003/m2449.978-5-317-06677-2.

Повний текст джерела

Анотація:

The optimal control of the metal solidification process in casting is considered. Quality of the obtained detail greatly depends on how the crystallization process proceeds. It is known that to obtain a model of a good quality it is desirable that the phase interface would be as close as possible to a plane and that the speed of its motion would be close to prescribed. The proposed mathematical model of the crystallization process is based on a three dimensional two phase initial-boundary value problem of the Stefan type. The velocity of the mold in the furnace is used as the control. The control satisfying the technological requirements is determined by solving the posed optimal control problem. The optimal control problem was solved numerically using gradient optimization methods. The effective method is proposed for calculation of the cost functional gradient. It is based on the fast automatic differentiation technique and produces the exact gradient for the chosen approximation of the optimal control problem.

Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "Fast Gradient Sign Method"

Muncsan, Tamás, and Attila Kiss. "Transferability of Fast Gradient Sign Method." In Advances in Intelligent Systems and Computing, 23–34. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-55187-2_3.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Xia, Xiaoyan, Wei Xue, Pengcheng Wan, Hui Zhang, Xinyu Wang, and Zhiting Zhang. "FCGSM: Fast Conjugate Gradient Sign Method for Adversarial Attack on Image Classification." In Lecture Notes in Electrical Engineering, 709–16. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-2287-1_98.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Wang, Jiangqin, and Wen Gao. "A Fast Sign Word Recognition Method for Chinese Sign Language." In Advances in Multimodal Interfaces — ICMI 2000, 599–606. Berlin, Heidelberg: Springer Berlin Heidelberg, 2000. http://dx.doi.org/10.1007/3-540-40063-x_78.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Tian, Zhiyi, Chenhan Zhang, Lei Cui, and Shui Yu. "GSMI: A Gradient Sign Optimization Based Model Inversion Method." In Lecture Notes in Computer Science, 67–78. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-97546-3_6.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Chen, Cheng, Zhiguang Wang, Yongnian Fan, Xue Zhang, Dawei Li, and Qiang Lu. "Nesterov Adam Iterative Fast Gradient Method for Adversarial Attacks." In Lecture Notes in Computer Science, 586–98. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-15919-0_49.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Necoara, I. "Rate Analysis of Inexact Dual Fast Gradient Method for Distributed MPC." In Intelligent Systems, Control and Automation: Science and Engineering, 163–78. Dordrecht: Springer Netherlands, 2013. http://dx.doi.org/10.1007/978-94-007-7006-5_10.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Chen, Li, Hongzhi Zhang, Dongwei Ren, David Zhang, and Wangmeng Zuo. "Fast Augmented Lagrangian Method for Image Smoothing with Hyper-Laplacian Gradient Prior." In Communications in Computer and Information Science, 12–21. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014. http://dx.doi.org/10.1007/978-3-662-45643-9_2.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Chernov, Alexey, Pavel Dvurechensky, and Alexander Gasnikov. "Fast Primal-Dual Gradient Method for Strongly Convex Minimization Problems with Linear Constraints." In Discrete Optimization and Operations Research, 391–403. Cham: Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-44914-2_31.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Cátedra, M. F., Rafael P. Torres, and Jesús G. Cuevas. "A method to analyze scattering from general periodic screens using Fast Fourier Transform and Conjugate Gradient method." In Electromagnetic Modelling and Measurements for Analysis and Synthesis Problems, 145–60. Dordrecht: Springer Netherlands, 1991. http://dx.doi.org/10.1007/978-94-011-3232-9_9.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Lin, Yuhui, Zhiyi Qu, Yu Zhang, and Huiyi Han. "A Fast and Accurate Pupil Localization Method Using Gray Gradient Differential and Curve Fitting." In Proceedings of the 4th International Conference on Computer Engineering and Networks, 495–503. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-11104-9_58.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "Fast Gradient Sign Method"

Liu, Yujie, Shuai Mao, Xiang Mei, Tao Yang, and Xuran Zhao. "Sensitivity of Adversarial Perturbation in Fast Gradient Sign Method." In 2019 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2019. http://dx.doi.org/10.1109/ssci44817.2019.9002856.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Xu, Jin. "Generate Adversarial Examples by Nesterov-momentum Iterative Fast Gradient Sign Method." In 2020 IEEE 11th International Conference on Software Engineering and Service Science (ICSESS). IEEE, 2020. http://dx.doi.org/10.1109/icsess49938.2020.9237700.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Hong, In-pyo, Gyu-ho Choi, Pan-koo Kim, and Chang Choi. "Security Verification Software Platform of Data-efficient Image Transformer Based on Fast Gradient Sign Method." In SAC '23: 38th ACM/SIGAPP Symposium on Applied Computing. New York, NY, USA: ACM, 2023. http://dx.doi.org/10.1145/3555776.3577731.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Hassan, Muhammad, Shahzad Younis, Ahmed Rasheed, and Muhammad Bilal. "Integrating single-shot Fast Gradient Sign Method (FGSM) with classical image processing techniques for generating adversarial attacks on deep learning classifiers." In Fourteenth International Conference on Machine Vision (ICMV 2021), edited by Wolfgang Osten, Dmitry Nikolaev, and Jianhong Zhou. SPIE, 2022. http://dx.doi.org/10.1117/12.2623585.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Reyes-Amezcua, Ivan, Gilberto Ochoa-Ruiz, and Andres Mendez-Vazquez. "Transfer Robustness to Downstream Tasks Through Sampling Adversarial Perturbations." In LatinX in AI at Computer Vision and Pattern Recognition Conference 2023. Journal of LatinX in AI Research, 2023. http://dx.doi.org/10.52591/lxai2023061811.

Повний текст джерела

Анотація:

Due to the vulnerability of deep neural networks to adversarial attacks, adversarial robustness has grown to be a crucial problem in deep learning. Recent research has demonstrated that even small perturbations to the input data can have a large impact on the model’s output, exposing them susceptible to malicious attacks. In this work, we propose Delta Data Augmentation (DDA), a data augmentation method for enhancing transfer robustness by sampling extracted perturbations from trained models against adversarial attacks. The main idea of our work is to generate adversarial perturbations and to apply them to downstream datasets in a data augmentation fashion. Here we demonstrate, through extensive experimentation the advantages of our data augmentation method over the current State-of-the-Art in Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks for CIFAR10 dataset.

Стилі APA, Harvard, Vancouver, ISO та ін.

Silva, Gabriel H. N. Espindola da, Rodrigo Sanches Miani, and Bruno Bogaz Zarpelão. "Investigando o Impacto de Amostras Adversárias na Detecção de Intrusões em um Sistema Ciberfísico." In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. Sociedade Brasileira de Computação - SBC, 2023. http://dx.doi.org/10.5753/sbrc.2023.488.

Повний текст джерела

Анотація:

Neste artigo, investigamos o impacto que amostras adversárias causam em algoritmos de aprendizado de máquina supervisionado utilizados para detectar ataques em um sistema ciberfísico. O estudo leva em consideração o cenário onde um atacante consegue obter acesso a dados do sistema alvo que podem ser utilizados para o treinamento do modelo adversário. O objetivo do atacante é gerar amostras maliciosas utilizando aprendizado de máquina adversário para enganar os modelos implementados para detecção de intrusão. Foi observado através dos ataques FGSM (Fast Gradient Sign Method) e JSMA (Jacobian Saliency Map Attack) que o conhecimento prévio da arquitetura do algoritmo alvo pode levar a ataques mais severos, e que os algoritmos alvo testados sofrem diferentes impactos conforme se varia o volume de dados roubados pelo atacante. Por fim, o método FGSM produziu ataques com maior severidade média que o JSMA, mas o JSMA apresenta a vantagem de ser menos invasivo e, possivelmente, mais difícil de ser detectado.

Стилі APA, Harvard, Vancouver, ISO та ін.

Mohandas, Sreenivasan, Naresh Manwani, and Durga Dhulipudi. "Momentum Iterative Gradient Sign Method Outperforms PGD Attacks." In 14th International Conference on Agents and Artificial Intelligence. SCITEPRESS - Science and Technology Publications, 2022. http://dx.doi.org/10.5220/0010938400003116.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Chen, Annie I., and Asuman Ozdaglar. "A fast distributed proximal-gradient method." In 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton). IEEE, 2012. http://dx.doi.org/10.1109/allerton.2012.6483273.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Mineo, Taiyo, and Hayaru Shouno. "Improving Convergence Rate of Sign Algorithm using Natural Gradient Method." In 2021 29th European Signal Processing Conference (EUSIPCO). IEEE, 2021. http://dx.doi.org/10.23919/eusipco54536.2021.9616060.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Sujee, R., and S. Padmavathi. "Fast Texture Classification using Gradient Histogram Method." In 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). IEEE, 2020. http://dx.doi.org/10.1109/icaccs48705.2020.9074355.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Звіти організацій з теми "Fast Gradient Sign Method"

Peter W. Carr, K.M. Fuller, D.R. Stoll, L.D. Steinkraus, M.S. Pasha, and Glenn G. Hardin. Fast Gradient Elution Reversed-Phase HPLC with Diode-Array Detection as a High Throughput Screening Method for Drugs of Abuse. Office of Scientific and Technical Information (OSTI), December 2005. http://dx.doi.org/10.2172/892807.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!