Deyue Zhang

Deyue Zhang, Yukun Guo, Jingzhi Li et al.

This work is concerned with the inverse source problem of locating multiple multipolar sources from boundary measurements for the Helmholtz equation. We develop simple and effective sampling schemes for location acquisition of the sources with a single wavenumber. Our algorithms are based on some novel indicator functions whose indicating behaviors could be used to locate multiple multipolar sources. The inversion schemes are totally "direct" in the sense that only simple integral calculations are involved in evaluating the indicator functions. Rigorous mathematical justifications are provided and extensive numerical examples are presented to demonstrate the effectiveness, robustness and efficiency of the proposed methods.

Heping Dong, Deyue Zhang, Yukun Guo

In this paper, we consider the inverse problem of determining the location and the shape of a sound-soft obstacle from the modulus of the far-field data for a single incident plane wave. By adding a reference ball artificially to the inverse scattering system, we propose a system of nonlinear integral equations based iterative scheme to reconstruct both the location and the shape of the obstacle. The reference ball technique causes few extra computational costs, but breaks the translation invariance and brings information about the location of the obstacle. Several validating numerical examples are provided to illustrate the effectiveness and robustness of the proposed inversion algorithm.

Zhao Liu, Quanchen Zou, Tian Yu et al.

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a daunting task due to their intricate implementation. Previous research on fuzzing ML frameworks has struggled to effectively extract input constraints and generate valid inputs, leading to extended fuzzing durations for deep execution or revealing the target crash. In this paper, we propose ConFL, a constraint-guided fuzzer for ML frameworks. ConFL automatically extracting constraints from kernel codes without the need for any prior knowledge. Guided by the constraints, ConFL is able to generate valid inputs that can pass the verification and explore deeper paths of kernel codes. In addition, we design a grouping technique to boost the fuzzing efficiency. To demonstrate the effectiveness of ConFL, we evaluated its performance mainly on Tensorflow. We find that ConFL is able to cover more code lines, and generate more valid inputs than state-of-the-art (SOTA) fuzzers. More importantly, ConFL found 84 previously unknown vulnerabilities in different versions of Tensorflow, all of which were assigned with new CVE ids, of which 3 were critical-severity and 13 were high-severity. We also extended ConFL to test PyTorch and Paddle, 7 vulnerabilities are found to date.

Qixue Xiao, Kang Li, Deyue Zhang et al.

Advance in deep learning algorithms overshadows their security risk in software implementations. This paper discloses a set of vulnerabilities in popular deep learning frameworks including Caffe, TensorFlow, and Torch. Contrast to the small code size of deep learning models, these deep learning frameworks are complex and contain heavy dependencies on numerous open source packages. This paper considers the risks caused by these vulnerabilities by studying their impact on common deep learning applications such as voice recognition and image classifications. By exploiting these framework implementations, attackers can launch denial-of-service attacks that crash or hang a deep learning application, or control-flow hijacking attacks that cause either system compromise or recognition evasions. The goal of this paper is to draw attention on the software implementations and call for the community effort to improve the security of deep learning frameworks.

Deyue Zhang, Fenglin Sun, Yan Ma et al.

This paper is concerned with the Fourier-Bessel method for the boundary value problems of the Helmholtz equation in a smooth simply connected domain. Based on the denseness of Fourier-Bessel functions, the problem can be approximated by determining the unknown coefficients in the linear combination. By the boundary conditions, an operator equation can be obtained. We derive a lower bound for the smallest singular value of the operator, and obtain a stability and convergence result for the regularized solution with a suitable choice of the regularization parameter. Numerical experiments are also presented to show the effectiveness of the proposed method.

Qixue Xiao, Kang Li, Deyue Zhang et al.

This paper considers security risks buried in the data processing pipeline in common deep learning applications. Deep learning models usually assume a fixed scale for their training and input data. To allow deep learning applications to handle a wide range of input data, popular frameworks, such as Caffe, TensorFlow, and Torch, all provide data scaling functions to resize input to the dimensions used by deep learning models. Image scaling algorithms are intended to preserve the visual features of an image after scaling. However, common image scaling algorithms are not designed to handle human crafted images. Attackers can make the scaling outputs look dramatically different from the corresponding input images. This paper presents a downscaling attack that targets the data scaling process in deep learning applications. By carefully crafting input data that mismatches with the dimension used by deep learning models, attackers can create deceiving effects. A deep learning application effectively consumes data that are not the same as those presented to users. The visual inconsistency enables practical evasion and data poisoning attacks to deep learning applications. This paper presents proof-of-concept attack samples to popular deep-learning-based image classification applications. To address the downscaling attacks, the paper also suggests multiple potential mitigation strategies.