arXiv subjects

Shuyu Cheng

Publications and source records attributed to Shuyu Cheng.

24 records · Page 2Linked to original sources

arXiv2021

Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks

We propose a simple and highly query-efficient black-box adversarial attack named SWITCH, which has a state-of-the-art performance in the score-based setting. SWITCH features a highly efficient and effective utilization of the gradient of a surrogate model $\hat{\mathbf{g}}$ w.r.t. the input image, i.e., the transferable gradient. In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function. We justify the choice of switching to the opposite direction by a local approximate linearity assumption. In SWITCH, only one or two queries are needed per iteration, but it is still effective due to the rich information provided by the transferable gradient, thereby resulting in unprecedented query efficiency. To improve the robustness of SWITCH, we further propose SWITCH$_\text{RGF}$ in which the update follows the direction of a random gradient-free (RGF) estimate when neither $\hat{\mathbf{g}}$ nor its opposite direction can increase the objective, while maintaining the advantage of SWITCH in terms of query efficiency. Experimental results conducted on CIFAR-10, CIFAR-100 and TinyImageNet show that compared with other methods, SWITCH achieves a satisfactory attack success rate using much fewer queries, and SWITCH$_\text{RGF}$ achieves the state-of-the-art attack success rate with fewer queries overall. Our approach can serve as a strong baseline for future black-box attacks because of its simplicity. The PyTorch source code is released on https://github.com/machanic/SWITCH.

cs.CV↗

arXiv2020

Improving Black-box Adversarial Attacks with a Transfer-based Prior

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. However, these methods often suffer from low attack success rates or poor query efficiency since it is non-trivial to estimate the gradient in a high-dimensional space with limited information. To address these problems, we propose a prior-guided random gradient-free (P-RGF) method to improve black-box adversarial attacks, which takes the advantage of a transfer-based prior and the query information simultaneously. The transfer-based prior given by the gradient of a surrogate model is appropriately integrated into our algorithm by an optimal coefficient derived by a theoretical analysis. Extensive experiments demonstrate that our method requires much fewer queries to attack black-box models with higher success rates compared with the alternative state-of-the-art methods.

cs.LG↗

arXiv2020

Magnetic Properties and Electronic Structure of Magnetic Topological Insulator MnBi$_2$Se$_4$

The intrinsic magnetic topological insulators MnBi$_2$X$_4$ (X = Se, Te) are promising candidates in realizing various novel topological states related to symmetry breaking by magnetic order. Although much progress had been made in MnBi$_2$Te$_4$, the study of MnBi$_2$Se$_4$ has been lacking due to the difficulty of material synthesis of the desired trigonal phase. Here, we report the synthesis of multilayer trigonal MnBi$_2$Se$_4$ with alternating-layer molecular beam epitaxy. Atomic-resolution scanning transmission electron microscopy (STEM) and scanning tunneling microscopy (STM) identify a well-ordered multilayer van der Waals (vdW) crystal with septuple-layer base units in agreement with the trigonal structure. Systematic thickness-dependent magnetometry studies illustrate the layered antiferromagnetic ordering as predicted by theory. Angle-resolved photoemission spectroscopy (ARPES) reveals the gapless Dirac-like surface state of MnBi$_2$Se$_4$, which demonstrates that MnBi$_2$Se$_4$ is a topological insulator above the magnetic ordering temperature. These systematic studies show that MnBi$_2$Se$_4$ is a promising candidate for exploring the rich topological phases of layered antiferromagnetic topological insulators.

cond-mat.mtrl-sci↗

arXiv2020

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior.

stat.ML↗

arXiv2019

Highly Mobile Carriers in a Candidate of Quasi-Two-Dimensional Topological Semimetal AuTe$_2$Br

We report the crystal and electronic structures of a non-centrosymmetric quasi-two-dimensional (2D), candidate of topological semimetal AuTe2Br. The Fermi surface of this layered compound consists of 2D-like, topological trivial electron and non-trivial hole pockets which host a Dirac cone along the kz direction. Our transport measurements on the single crystals show highly anisotropic, compensated low-density electrons and holes, both of which exhibit ultrahigh mobility at a level of 10^5cm^2V^-1s^-1 at low temperature. The highly mobile, compensated carriers lead a non-saturated, parabolic magnetoresistance as large as 3*10^5 in single-crystalline AuTe2Br in a magnetic field up to 58 T.

cond-mat.mtrl-sci↗

arXiv2019

Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to reduce the high variance of noisy stochastic gradients, Dubey et al. [2016] applied the standard variance reduction technique on stochastic gradient Langevin dynamics and obtained both theoretical and experimental improvements. In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics. Moreover, we apply the symmetric splitting scheme in our variance-reduced Hamiltonian Monte Carlo algorithms to further improve the theoretical results. The experimental results are also consistent with the theoretical results. As our experiment shows, variance-reduced Hamiltonian Monte Carlo demonstrates better performance than variance-reduced Langevin dynamics in Bayesian regression and classification tasks on real-world datasets.

cs.LG↗