arXiv subjects

Weiqi Peng

Publications and source records attributed to Weiqi Peng.

7 recordsLinked to original sources

arXiv2022

Long-time asymptotics for a fourth-order dispersive nonlinear Schrödinger equation with nonzero boundary conditions

In this work, we consider the long-time asymptotics for the Cauchy problem of a fourth-order dispersive nonlinear Schrödinger equation with nonzero boundary conditions at infinity. Firstly, in order to construct the basic Riemann-Hilbert problem associated with nonzero boundary conditions, we analysis direct scattering problem. Then we deform the corresponding matrix Riemann-Hilbert problem to explicitly solving models via using the nonlinear steepest descent method and employing the $g$-function mechanism to eliminate the exponential growths of the jump matrices. Finally, we obtain the asymptotic stage of modulation instability for the fourth-order dispersive nonlinear Schrödinger equation.

math.AP↗

arXiv2022

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. However, in certain scenarios, people may not want their data being used for training commercial models and thus studied how to attack the learnability of deep learning models. Previous works on learnability attack only consider the goal of preventing unauthorized exploitation on the specific dataset but not the process of restoring the learnability for authorized cases. To tackle this issue, this paper introduces and investigates a new concept called "learnability lock" for controlling the model's learnability on a specific dataset with a special key. In particular, we propose adversarial invertible transformation, that can be viewed as a mapping from image to image, to slightly modify data samples so that they become "unlearnable" by machine learning models with negligible loss of visual features. Meanwhile, one can unlock the learnability of the dataset and train models normally using the corresponding key. The proposed learnability lock leverages class-wise perturbation that applies a universal transformation function on data samples of the same label. This ensures that the learnability can be easily restored with a simple inverse transformation while remaining difficult to be detected or reverse-engineered. We empirically demonstrate the success and practicability of our method on visual classification tasks.

cs.LG↗

arXiv2021

Bound-state soliton and rogue wave solutions for the sixth-order nonlinear Schrödinger equation via inverse scattering transform method

In this work, inverse scattering transform for the sixth-order nonlinear Schrödinger equation with both zero and nonzero boundary conditions at infinity is given, respectively. For the case of zero nonzero boundary conditions, in terms of the Laurent's series and generalization of the residue theorem, the bound-state soliton is derived. For nonzero boundary conditions, using the robust inverse scattering transform, we present a matrix Riemann-Hilbert problem of the sixth-order nonlinear Schrödinger equation. Then based on the obtained Riemann-Hilbert problem, the rogue wave and breather wave solutions are derived through a modified Darboux transformation. Besides, according to some appropriate parameters choices, several graphical analyses are provided to discuss the dynamical behaviors of the bound-state soliton and rogue wave solutions, and analyse how the higher-order terms affect the bound-state soliton and rogue wave.

nlin.SI↗

arXiv2021

Double and triple poles solutions for the Gerdjikov-Ivanov type of derivative nonlinear Schrödinger equation with zero/nonzero boundary conditions

In this work, the double and triple poles soliton solutions for the Gerdjikov-Ivanov(GI) type of derivative nonlinear Schrödinger equation with zero boundary conditions(ZBCs) and nonzero boundary conditions(NZBCs) are studied via Riemann-Hilbert (RH) method. Though spectral problem analysis, we first give out the Jost function and scattering matrix under ZBCs and NZBCs. Then according to the analyticity, symmetry and asymptotic behavior of Jost function and scattering matrix, the Riemann-Hilbert problem(RHP) with ZBCs and NZBCs are constructed. Further, the obtained RHP with ZBCs and NZBCs can be solved in the case that reflection coefficients have double or triple poles. Finally, we derive the general precise formulae of N-double and N-triple poles solutions corresponding to ZBCs and NZBCs, respectively. The dynamical behaviors for these solutions are further discussed by image simulation.

nlin.SI↗

arXiv2021

The data-driven localized wave solutions of the derivative nonlinear Schrodinger equation by using improved PINN approach

The research of the derivative nonlinear Schrodinger equation (DNLS) has attracted more and more extensive attention in theoretical analysis and physical application. The improved physicsinformed neural network (IPINN) approach with neuron-wise locally adaptive activation function is presented to derive the data-driven localized wave solutions, which contain rational solution, soliton solution, rogue wave, periodic wave and rogue periodic wave for the DNLS with initial and boundary conditions in complex space. Especially, the data-driven periodic wave and rogue periodic wave of the DNLS are investigated by employing the IPINN method for the first time. Furthermore, the relevant dynamical behaviors, error analysis and vivid plots have been exhibited in detail. The numerical results indicate the IPINN method can well simulate the localized wave solutions of the DNLS under a small data set.

nlin.SI↗

arXiv2021

PINN deep learning for the Chen-Lee-Liu equation: Rogue wave on the periodic background

We consider the exact rogue periodic wave (rogue wave on the periodic background) and periodic wave solutions for the Chen-Lee-Liu equation via the odd-th order Darboux transformation. Then, the multi-layer physics-informed neural networks (PINNs) deep learning method is applied to research the data-driven rogue periodic wave, breather wave, soliton wave and periodic wave solutions of well-known Chen-Lee-Liu equation. Especially, the data-driven rogue periodic wave is learned for the first time to solve the partial differential equation. In addition, using image simulation, the relevant dynamical behaviors and error analysis for there solutions are presented. The numerical results indicate that the rogue periodic wave, breather wave, soliton wave and periodic wave solutions for Chen-Lee-Liu equation can be generated well by PINNs deep learning method.

nlin.SI↗

arXiv2020

One-pixel Signature: Characterizing CNN Models for Backdoor Detection

We tackle the convolution neural networks (CNNs) backdoor detection problem by proposing a new representation called one-pixel signature. Our task is to detect/classify if a CNN model has been maliciously inserted with an unknown Trojan trigger or not. Here, each CNN model is associated with a signature that is created by generating, pixel-by-pixel, an adversarial value that is the result of the largest change to the class prediction. The one-pixel signature is agnostic to the design choice of CNN architectures, and how they were trained. It can be computed efficiently for a black-box CNN model without accessing the network parameters. Our proposed one-pixel signature demonstrates a substantial improvement (by around 30% in the absolute detection accuracy) over the existing competing methods for backdoored CNN detection/classification. One-pixel signature is a general representation that can be used to characterize CNN models beyond backdoor detection.

cs.CV↗