Search arXiv⌕ Search

arXiv subjects

Li Chen

Publications and source records attributed to Li Chen.

At least 595 records · Page 33Linked to original sources
arXiv2019

BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading

Diabetic retinopathy (DR) is a common retinal disease that leads to blindness. For diagnosis purposes, DR image grading aims to provide automatic DR grade classification, which is not addressed in conventional research methods of binary DR image classification. Small objects in the eye images, like lesions and microaneurysms, are essential to DR grading in medical imaging, but they could easily be influenced by other objects. To address these challenges, we propose a new deep learning architecture, called BiRA-Net, which combines the attention model for feature extraction and bilinear model for fine-grained classification. Furthermore, in considering the distance between different grades of different DR categories, we propose a new loss function, called grading loss, which leads to improved training convergence of the proposed approach. Experimental results are provided to demonstrate the superior performance of the proposed approach.

cs.CV↗
arXiv2019

An End-to-End Block Autoencoder For Physical Layer Based On Neural Networks

Deep Learning has been widely applied in the area of image processing and natural language processing. In this paper, we propose an end-to-end communication structure based on autoencoder where the transceiver can be optimized jointly. A neural network roles as a combination of channel encoder and modulator. In order to deal with input sequences parallelly, we introduce block scheme, which means that the autoencoder divides the input sequence into a series of blocks. Each block contains fixed number of bits for encoding and modulating operation. Through training, the proposed system is able to produce the modulated constellation diagram of each block. The simulation results show that our autoencoder performs better than other autoencoder-based systems under additive Gaussian white noise (AWGN) and fading channels. We also prove that the bit error rate (BER) of proposed system can achieve an acceptable range with increasing the number of symbols.

cs.IT↗
arXiv2019

Sparse Representation Classification via Screening for Graphs

The sparse representation classifier (SRC) is shown to work well for image recognition problems that satisfy a subspace assumption. In this paper we propose a new implementation of SRC via screening, establish its equivalence to the original SRC under regularity conditions, and prove its classification consistency for random graphs drawn from stochastic blockmodels. The results are demonstrated via simulations and real data experiments, where the new algorithm achieves comparable numerical performance but significantly faster.

cs.LG↗
arXiv2019

The Mean Field Kinetic Equation for Interacting Particle Systems with Non-Lipschitz Force

In this paper, we prove the global existence of the weak solution to the mean field kinetic equation derived from the $N$-particle Newtonian system. For $L^1\cap L^\infty$ initial data, the solvability of the mean field kinetic equation can be obtained by using uniform estimates and compactness arguments while the difficulties arising from the non-local non-linear interaction are tackled appropriately using the Aubin-Lions compact embedding theorem.

math.AP↗
arXiv2019

Long term variability of Swift J1753.5-0127]{Long term variability of Swift J1753.5-0127: X-ray spectral-temporal correlations during state transitions

We studied the long-term evolution of the spectral-temporal correlated properties of the black hole candidate Swift J1753.5-0127 from the onset of its outburst until 2011 with the Rossi X-ray Timing Explorer (RXTE). The source stayed most of its lifetime during hard state, with occasionally transitioned to the hard intermediate state. Similar to typical black hole transients, Swift J1753.5-0127 traces a clear hard line in absolute rms - intensity diagram during the low hard state, with expected highest absolute rms, while shows a clear turn during the hard intermediate state, accompanied by lower absolute rms. Different from Cyg X-1, we found that frequency-dependent time lag increased significantly in the 0.02 -- 3.2 Hz band during state transition in this source. The X-ray time lags in 0.02 -- 3.2 Hz can therefore be used as indicators of state transition in this source. Type-C QPO frequency is positively related with its fractional rms and X-ray photon index, suggesting a moving inwards disk/corona scenario. We discussed the physical interpretation of our results in our paper.

astro-ph.HE↗
arXiv2019

Towards resilient machine learning for ransomware detection

There has been a surge of interest in using machine learning (ML) to automatically detect malware through their dynamic behaviors. These approaches have achieved significant improvement in detection rates and lower false positive rates at large scale compared with traditional malware analysis methods. ML in threat detection has demonstrated to be a good cop to guard platform security. However it is imperative to evaluate - is ML-powered security resilient enough? In this paper, we juxtapose the resiliency and trustworthiness of ML algorithms for security, via a case study of evaluating the resiliency of ransomware detection via the generative adversarial network (GAN). In this case study, we propose to use GAN to automatically produce dynamic features that exhibit generalized malicious behaviors that can reduce the efficacy of black-box ransomware classifiers. We examine the quality of the GAN-generated samples by comparing the statistical similarity of these samples to real ransomware and benign software. Further we investigate the latent subspace where the GAN-generated samples lie and explore reasons why such samples cause a certain class of ransomware classifiers to degrade in performance. Our focus is to emphasize necessary defense improvement in ML-based approaches for ransomware detection before deployment in the wild. Our results and discoveries should pose relevant questions for defenders such as how ML models can be made more resilient for robust enforcement of security objectives.

cs.LG↗
arXiv2019

Privacy Preserving Adjacency Spectral Embedding on Stochastic Blockmodels

For graphs generated from stochastic blockmodels, adjacency spectral embedding is asymptotically consistent. Further, adjacency spectral embedding composed with universally consistent classifiers is universally consistent to achieve the Bayes error. However when the graph contains private or sensitive information, treating the data as non-private can potentially leak privacy and incur disclosure risks. In this paper, we propose a differentially private adjacency spectral embedding algorithm for stochastic blockmodels. We demonstrate that our proposed methodology can estimate the latent positions close to, in Frobenius norm, the latent positions by adjacency spectral embedding and achieve comparable accuracy at desired privacy parameters in simulated and real world networks.

cs.LG↗
arXiv2019

Symmetric properties for Choquard equations involving fully nonlinear nonlocal operator

In this paper, the positive solutions to Choquard equation involving fully nonlinear nonlocal operator are shown to be symmetric and monotone by using the moving plane method which has been introduced by Chen, Li and Li in 2015. The key ingredients are to obtain the "narrow region principle" and "decay at infinity" for the corresponding problems. Similar ideas can be easily applied to various nonlocal problems with more general nonlinearities.

math.AP↗
arXiv2019

Lattice symmetry assisted second order topological superconductors and Majorana patterns

We propose a realization of the lattice symmetry assisted second order topological superconductors with corner Majorana zero modes (MZM) based on two-dimensional topological insulators (2DTI). The lattice symmetry can naturally lead to the anisotropic coupling of edge states along different directions to the in-plane magnetic field and conventional s-wave pairings, thus leading to a single MZM locating at the corners for various lattice patterns. In particular, we focus on the 2DTI with D$_{3d}$ lattice symmetry and found different types of gap opening for the edge states along the armchair and zigzag edges in a broad range of parameters. As a consequence, a single MZM exists at the corner between the zigzag and armchair edges, and is robust against weakly lattice symmetry broken. We propose to realize such corner MZMs in a variety of polygon patterns, such as triangles and quadrilaterals. We further show their potentials in building the Majorana network through constructing the Majorana Y-junction under an in-plane magnetic field.

cond-mat.mes-hall↗
arXiv2019

To believe or not to believe: Validating explanation fidelity for dynamic malware analysis

Converting malware into images followed by vision-based deep learning algorithms has shown superior threat detection efficacy compared with classical machine learning algorithms. When malware are visualized as images, visual-based interpretation schemes can also be applied to extract insights of why individual samples are classified as malicious. In this work, via two case studies of dynamic malware classification, we extend the local interpretable model-agnostic explanation algorithm to explain image-based dynamic malware classification and examine its interpretation fidelity. For both case studies, we first train deep learning models via transfer learning on malware images, demonstrate high classification effectiveness, apply an explanation method on the images, and correlate the results back to the samples to validate whether the algorithmic insights are consistent with security domain expertise. In our first case study, the interpretation framework identifies indirect calls that uniquely characterize the underlying exploit behavior of a malware family. In our second case study, the interpretation framework extracts insightful information such as cryptography-related APIs when applied on images created from API existence, but generate ambiguous interpretation on images created from API sequences and frequencies. Our findings indicate that current image-based interpretation techniques are promising for explaining vision-based malware classification. We continue to develop image-based interpretation schemes specifically for security applications.

cs.CR↗
arXiv2019

Ranking-Based Autoencoder for Extreme Multi-label Classification

Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions. XML is more and more on demand in the Internet industries, accompanied with the increasing business scale / scope and data accumulation. The extremely large label collections yield challenges such as computational complexity, inter-label dependency and noisy labeling. Many methods have been proposed to tackle these challenges, based on different mathematical formulations. In this paper, we propose a deep learning XML method, with a word-vector-based self-attention, followed by a ranking-based AutoEncoder architecture. The proposed method has three major advantages: 1) the autoencoder simultaneously considers the inter-label dependencies and the feature-label dependencies, by projecting labels and features onto a common embedding space; 2) the ranking loss not only improves the training efficiency and accuracy but also can be extended to handle noisy labeled data; 3) the efficient attention mechanism improves feature representation by highlighting feature importance. Experimental results on benchmark datasets show the proposed method is competitive to state-of-the-art methods.

cs.LG↗
arXiv2019

Understanding the efficacy, reliability and resiliency of computer vision techniques for malware detection and future research directions

My research lies in the intersection of security and machine learning. This overview summarizes one component of my research: combining computer vision with malware exploit detection for enhanced security solutions. I will present the perspectives of efficacy, reliability and resiliency to formulate threat detection as computer vision problems and develop state-of-the-art image-based malware classification. Representing malware binary as images provides a direct visualization of data samples, reduces the efforts for feature extraction, and consumes the whole binary for holistic structural analysis. Employing transfer learning of deep neural networks effective for large scale image classification to malware classification demonstrates superior classification efficacy compared with classical machine learning algorithms. To enhance reliability of these vision-based malware detectors, interpretation frameworks can be constructed on the malware visual representations and useful for extracting faithful explanation, so that security practitioners have confidence in the model before deployment. In cyber-security applications, we should always assume that a malware writer constantly modifies code to bypass detection. Addressing the resiliency of the malware detectors is equivalently important as efficacy and reliability. Via understanding the attack surfaces of machine learning models used for malware detection, we can greatly improve the robustness of the algorithms to combat malware adversaries in the wild. Finally I will discuss future research directions worth pursuing in this research community.

cs.CR↗
arXiv2019

The substructure and halo population of the Double Cluster $h$ and $χ$ Persei

In order to study the stellar population and possible substructures in the outskirts of Double Cluster $h$ and $χ$ Persei, we investigate using the GAIA DR2 data a sky area of about 7.5 degrees in radius around the Double Cluster cores. We identify member stars using various criteria, including their kinematics (viz, proper motion), individual parallaxes, as well as photometric properties. A total of 2186 member stars in the parameter space were identified as members. Based on the spatial distribution of the member stars, we find an extended halo structure of $h$ and $χ$ Persei, about 6 - 8 times larger than their core radii. We report the discovery of filamentary substructures extending to about 200 pc away from the Double Cluster. The tangential velocities of these distant substructures suggest that they are more likely to be the remnants of primordial structures, instead of a tidally disrupted stream from the cluster cores. Moreover, the internal kinematic analysis indicates that halo stars seems to be experiencing a dynamic stretching in the RA direction, while the impact of the core components is relatively negligible. This work also suggests that the physical scale and internal motions of young massive star clusters may be more complex than previously thought.

astro-ph.GA↗
arXiv2019

Nonuniform Mean-square Exponential Dichotomies and Mean-square Exponential Stability

In this paper, the existence conditions of nonuniform mean-square exponential dichotomy (NMS-ED) for a linear stochastic differential equation (SDE) are established. The difference of the conditions for the existence of a nonuniform dichotomy between an SDE and an ordinary differential equation (ODE) is that the first one needs an additional assumption, nonuniform Lyapunov matrix, to guarantee that the linear SDE can be transformed into a decoupled one, while the second does not. Therefore, the first main novelty of our work is that we establish some preliminary results to tackle the stochasticity. This paper is also concerned with the mean-square exponential stability of nonlinear perturbation of a linear SDE under the condition of nonuniform mean-square exponential contraction (NMS-EC). For this purpose, the concept of second-moment regularity coefficient is introduced. This concept is essential in determining the stability of the perturbed equation, and hence we deduce the lower and upper bounds of this coefficient. Our results imply that the lower and upper bounds of the second-moment regularity coefficient can be expressed solely by the drift term of the linear SDE.

math.DS↗
arXiv2019

Understanding the Importance of Single Directions via Representative Substitution

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid much attention given their fundamental role. However, recent research (Morcos et al. 2018) presented a counterintuitive phenomenon, which suggests that an individual unit with high class selectivity, called interpretable units, has poor contributions to generalization of DNNs. In this work, we provide a new perspective to understand this counterintuitive phenomenon, which makes sense when we introduce Representative Substitution (RS). Instead of individually selective units with classes, the RS refers to the independence of a unit's representations in the same layer without any annotation. Our experiments demonstrate that interpretable units have high RS which are not critical to network's generalization. The RS provides new insights into the interpretation of DNNs and suggests that we need to focus on the independence and relationship of the representations.

cs.LG↗
arXiv2018

Deep Transfer Learning for Static Malware Classification

We propose to apply deep transfer learning from computer vision to static malware classification. In the transfer learning scheme, we borrow knowledge from natural images or objects and apply to the target domain of static malware detection. As a result, training time of deep neural networks is accelerated while high classification performance is still maintained. We demonstrate the effectiveness of our approach on three experiments and show that our proposed method outperforms other classical machine learning methods measured in accuracy, false positive rate, true positive rate and $F_1$ score (in binary classification). We instrument an interpretation component to the algorithm and provide interpretable explanations to enhance security practitioners' trust to the model. We further discuss a convex combination scheme of transfer learning and training from scratch for enhanced malware detection, and provide insights of the algorithmic interpretation of vision-based malware classification techniques.

cs.LG↗