Recent studies have shown that Graph Convolutional Networks (GCNs) are vulnerable to adversarial attacks on the graph structure. Although multiple works have been proposed to improve their robustness against such structural adversarial attacks, the reasons for the success of the attacks remain unclear. In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i.e., the weighted mean) of GCNs. Specifically, our analysis takes advantage of the breakdown point which can quantitatively measure the robustness of aggregation schemes. The key insight is that weighted mean, as the basic design of GCNs, has a low breakdown point and its output can be dramatically changed by injecting a single edge. We show that adopting the aggregation scheme with a high breakdown point (e.g., median or trimmed mean) could significantly enhance the robustness of GCNs against structural attacks. Extensive experiments on four real-world datasets demonstrate that such a simple but effective method achieves the best robustness performance compared to state-of-the-art models.
This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adversarial attacks than other neural networks. However, our experiments show that capsule networks can be fooled as easily as convolutional neural networks.
The video-based action recognition task has been extensively studied in recent years. In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame attack that adds an inconspicuous perturbation to only a single frame of a given video clip. Our analysis shows that the models are highly vulnerable against the one frame attack due to their structural properties. Experiments demonstrate high fooling rates and inconspicuous characteristics of the attack. Furthermore, we show that strong universal one frame p…
University of California, Davis（加州大学戴维斯分校）；Visa Research（Visa研究院）；Linköping University（林雪平大学）
Adversarial attacks on a convolutional neural network (CNN) -- injecting human-imperceptible perturbations into an input image -- could fool a high-performance CNN into making incorrect predictions. The success of adversarial attacks raises serious concerns about the robustness of CNNs, and prevents them from being used in safety-critical applications, such as medical diagnosis and autonomous driving. Our work introduces a visual analytics approach to understanding adversarial attacks by answering two questions: (1) which neurons are more vulnerable to attacks and (2) which image features do t…
University of California Santa Barbara（加州大学圣巴巴拉分校）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Institute of Numerical Mathematics of Russian Academy of Sciences（俄罗斯科学院数值数学研究所）
Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability and deep neural networks using active subspace. Firstly, we employ the active subspace to measure the number of "active neurons" at each intermediate layer and reduce the number of neurons from several thousands to several dozens. This motivates us to change the network structure and to develop a new and more compact network, referred to as {ASNet}, that has significantly fewer model parameters. Secondly, we propose an…
University of California, Irvine（加州大学欧文分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
Mass segmentation is an important task in mammogram analysis, providing effective morphological features and regions of interest (ROI) for mass detection and classification. Inspired by the success of using deep convolutional features for natural image analysis and conditional random fields (CRF) for structural learning, we propose an end-to-end network for mammographic mass segmentation. The network employs a fully convolutional network (FCN) to model potential function, followed by a CRF to perform structural learning. Because the mass distribution varies greatly with pixel position, the FCN…
Sichuan University（四川大学）；Huazhong University of Science and Technology（华中科技大学）；Delft University of Technology（代尔夫特理工大学）
Recent studies have revealed the vulnerability of graph convolutional networks (GCNs) to edge-perturbing attacks, such as maliciously inserting or deleting graph edges. However, a theoretical proof of such vulnerability remains a big challenge, and effective defense schemes are still open issues. In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks. Following this, an anonymous graph convolutional network, named AN-GCN, is proposed to counter against edge-perturbing attacks. Speci…
Huazhong University of Science and Technology（华中科技大学）
Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering. One such application is electroencephalogram (EEG) based brain-computer interface (BCI), where multiple convolutional neural network (CNN) models have been proposed for EEG classification. However, it has been found that deep learning models can be easily fooled with adversarial examples, which are normal examples with small deliberate perturbations. This paper proposes an unsupervised fast gradient sign method (UFGSM) to attack three pop…
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）；Sun Yat-sen University（中山大学）
Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact architectures. In this study, we claim that identifying structural redundancy plays a more essential role than finding unimportant filters, theoretically and empirically. We first statistically model the network pruning problem in a redundancy reduction perspective and find that pruning in the layer(s) with the most structural redundancy outperfor…
Dalian University of Technology（大连理工大学）；The American University in Cairo（开罗美国大学）
In this paper, a mechanistic data-driven approach is proposed to accelerate structural topology optimization, employing an in-house developed finite element convolutional neural network (FE-CNN). Our approach can be divided into two stages: offline training, and online optimization. During offline training, a mapping function is built between high and low resolution representations of a given design domain. The mapping is expressed by a FE-CNN, which targets a common objective function value (e.g., structural compliance) across design domains of differing resolutions. During online optimizatio…
Graph structural information such as topologies or connectivities provides valuable guidance for graph convolutional networks (GCNs) to learn nodes' representations. Existing GCN models that capture nodes' structural information weight in- and out-neighbors equally or differentiate in- and out-neighbors globally without considering nodes' local topologies. We observe that in- and out-neighbors contribute differently for nodes with different local topologies. To explore the directional structural information for different nodes, we propose a GCN model with weighted structural features, named WG…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Zhejiang University（浙江大学）
Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a novel 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervise…
Guiding the retraining of convolutional neural networks against adversarial inputs
Universitat Politècnica de Catalunya - BarcelonaTech（加泰罗尼亚理工大学-巴塞罗那理工学院）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）；University of Innsbruck（因斯布鲁克大学）
Technical University of Munich（慕尼黑工业大学）；University of Southern California（南加州大学）
Convolutional Neural Networks (CNNs) have emerged as highly successful tools for image generation, recovery, and restoration. A major contributing factor to this success is that convolutional networks impose strong prior assumptions about natural images. A surprising experiment that highlights this architectural bias towards natural images is that one can remove noise and corruptions from a natural image without using any training data, by simply fitting (via gradient descent) a randomly initialized, over-parameterized convolutional generator to the corrupted image. While this over-parameteriz…
United International University（联合国际大学）；University of Tehran（德黑兰大学）
The task of drug-target interaction prediction holds significant importance in pharmacology and therapeutic drug design. In this paper, we present FRnet-DTI, an auto encoder and a convolutional classifier for feature manipulation and drug target interaction prediction. Two convolutional neural neworks are proposed where one model is used for feature manipulation and the other one for classification. Using the first method FRnet-1, we generate 4096 features for each of the instances in each of the datasets and use the second method, FRnet-2, to identify interaction probability employing those f…
Chongqing Jiaotong University（重庆交通大学）；Institute for Infocomm Research (I2R), A*STAR（新加坡科技研究局资讯通信研究院（I2R））；Hunan University（湖南大学）
Structural damage detection has become an interdisciplinary area of interest for various engineering fields, while the available damage detection methods are being in the process of adapting machine learning concepts. Most machine learning based methods heavily depend on extracted ``hand-crafted" features that are manually selected in advance by domain experts and then, fixed. Recently, deep learning has demonstrated remarkable performance on traditional challenging tasks, such as image classification, object detection, etc., due to the powerful feature learning capabilities. This breakthrough…
Korea University（高丽大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Connected and autonomous vehicles (CAVs) are an innovative form of traditional vehicles. Automotive Ethernet replaces the controller area network and FlexRay to support the large throughput required by high-definition applications. As CAVs have numerous functions, they exhibit a large attack surface and an increased vulnerability to attacks. However, no previous studies have focused on intrusion detection in automotive Ethernet-based networks. In this paper, we present an intrusion detection method for detecting audio-video transport protocol (AVTP) stream injection attacks in automotive Ether…
Qazvin Azad University（加兹温阿扎德大学）；The University of Leeds（利兹大学）
CAPTCHA is a human-centred test to distinguish a human operator from bots, attacking programs, or other computerised agents that tries to imitate human intelligence. In this research, we investigate a way to crack visual CAPTCHA tests by an automated deep learning based solution. The goal of this research is to investigate the weaknesses and vulnerabilities of the CAPTCHA generator systems; hence, developing more robust CAPTCHAs, without taking the risks of manual try and fail efforts. We develop a Convolutional Neural Network called Deep-CAPTCHA to achieve this goal. The proposed platform is …
School of Computer Science and Technology（计算机科学与技术学院）
Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be vulnerable to the structural attacks and noises. To address this issue, we propose a novel Latent Graph Convolutional Representation (LatGCR) for robust graph data representation and learning. Our LatGCR is derived based on reformulating graph convolutional representation from the aspect of graph neighborhood reconstruction. Given an input graph $\textbf{A}$, Lat…
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes the application of convolutional masks straightforward for time series data, such as video applications, but many high-dimensional time series data are not organised in regular lattices, and instead values may have adjacency relationships with non-trivial topologies, such as small-world networks or trees. In our application ca…
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier basis functions. By exploiting this sensitivity, they proposed a simple black-box adversarial attack: Single Fourier attack. To reduce structural sensitivity, we can use regularization of convolution filter weights since the sensitivity of linear transform can be assessed by the nor…
In this work, we exploit convolutional neural networks (CNNs) for the classification of very high resolution (VHR) polarimetric SAR (PolSAR) data. Due to the significant appearance of heterogeneous textures within these data, not only polarimetric features but also structural tensors are exploited to feed CNN models. For deep networks, we use the SegNet model for semantic segmentation, which corresponds to pixelwise classification in remote sensing. Our experiments on the airborne F-SAR data show that for VHR PolSAR images, SegNet could provide high accuracy for the classification task; and in…
University of Central Florida（中佛罗里达大学）；Iowa State University（爱荷华州立大学）
Structural Health Monitoring (SHM) has been continuously benefiting from the advancements in the field of data science. Various types of Artificial Intelligence (AI) methods have been utilized for the assessment and evaluation of civil structures. In AI, Machine Learning (ML) and Deep Learning (DL) algorithms require plenty of datasets to train; particularly, the more data DL models are trained with, the better output it yields. Yet, in SHM applications, collecting data from civil structures through sensors is expensive and obtaining useful data (damage associated data) is challenging. In this…
Central University of Finance and Economics（中央财经大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of York（约克大学）
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Exp…
The Mean Square Error (MSE) has shown its strength when applied in deep generative models such as Auto-Encoders to model reconstruction loss. However, in image domain especially, the limitation of MSE is obvious: it assumes pixel independence and ignores spatial relationships of samples. This contradicts most architectures of Auto-Encoders which use convolutional layers to extract spatial dependent features. We base on the structural similarity metric (SSIM) and propose a novel level weighted structural similarity (LWSSIM) loss for convolutional Auto-Encoders. Experiments on common datasets on…
The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear elastic cantilevered structures subjected to external static loads at its free end using convolutional neural networks (CNN). Two different architectures are implemented that take as input the structure geometry, external loads, and displacement boundary conditions, and output th…
Multi-Head Graph Convolutional Network for Structural Connectome Classification
Athinoula A. Martinos Center for Biomedical Imaging（阿西努拉·A·马蒂诺斯生物医学成像中心）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Massachusetts Institute of Technology（麻省理工学院）
Technische Universität München（慕尼黑工业大学）；Klinikum der Universität München（慕尼黑大学附属医院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Structural data from Electronic Health Records as complementary information to imaging data for disease prediction. We incorporate novel weighting layer into the Graph Convolutional Networks, which weights every element of structural data by exploring its relation to the underlying disease. We demonstrate the superiority of our developed technique in terms of computational speed and obtained encouraging results where our method outperforms the state-of-the-art methods when applied to two publicly available datasets ABIDE and Chest X-ray in terms of relative performance for the accuracy of pred…
Graph representation learning is a fundamental task in various applications that strives to learn low-dimensional embeddings for nodes that can preserve graph topology information. However, many existing methods focus on static graphs while ignoring evolving graph patterns. Inspired by the success of graph convolutional networks(GCNs) in static graph embedding, we propose a novel k-core based temporal graph convolutional network, the CTGCN, to learn node representations for dynamic graphs. In contrast to previous dynamic graph embedding methods, CTGCN can preserve both local connective proximi…
The use of deep neural network (DNN) models as surrogates for linear and nonlinear structural dynamical systems is explored. The goal is to develop DNN based surrogates to predict structural response, i.e., displacements and accelerations, for given input (harmonic) excitations. In particular, the focus is on the development of efficient network architectures using fully-connected, sparsely-connected, and convolutional network layers, and on the corresponding training strategies that can provide a balance between the overall network complexity and prediction accuracy in the target dataspaces. …
Politecnico di Milano（米兰理工大学）；MOX - Dipartimento di Matematica, Politecnico di Milano（米兰理工大学MOX - 数学系）；Dipartimento di Ingegneria Civile e Ambientale, Politecnico di Milano（米兰理工大学土木工程与环境工程系）
We propose a novel approach to Structural Health Monitoring (SHM), aiming at the automatic identification of damage-sensitive features from data acquired through pervasive sensor systems. Damage detection and localization are formulated as classification problems, and tackled through Fully Convolutional Networks (FCNs). A supervised training of the proposed network architecture is performed on data extracted from numerical simulations of a physics-based model (playing the role of digital twin of the structure to be monitored) accounting for different damage scenarios. By relying on this simpli…
Huazhong University of Science and Technology（华中科技大学）
Deep learning models for graphs, especially Graph Convolutional Networks (GCNs), have achieved remarkable performance in the task of semi-supervised node classification. However, recent studies show that GCNs suffer from adversarial perturbations. Such vulnerability to adversarial attacks significantly decreases the stability of GCNs when being applied to security-critical applications. Defense methods such as preprocessing, attention mechanism and adversarial training have been discussed by various studies. While being able to achieve desirable performance when the perturbation rates are low,…
Lakehead University（湖首大学）；University of Calgary（卡尔加里大学）
Objective: This paper presents an Alzheimer's disease (AD) detection method based on learning structural similarity between Magnetic Resonance Images (MRIs) and representing this similarity as a graph. Methods: We construct the similarity graph using embedded features of the input image (i.e., Non-Demented (ND), Very Mild Demented (VMD), Mild Demented (MD), and Moderated Demented (MDTD)). We experiment and compare different dimension-reduction and clustering algorithms to construct the best similarity graph to capture the similarity between the same class images using the cosine distance as a …
University of Washington（华盛顿大学）；Cleveland Clinic Foundation（克利夫兰诊所基金会）；Google AI Healthcare（谷歌AI医疗）
Seizure detection from EEGs is a challenging and time consuming clinical problem that would benefit from the development of automated algorithms. EEGs can be viewed as structural time series, because they are multivariate time series where the placement of leads on a patient's scalp provides prior information about the structure of interactions. Commonly used deep learning models for time series don't offer a way to leverage structural information, but this would be desirable in a model for structural time series. To address this challenge, we propose the temporal graph convolutional network (…
Motivation: Thanks to the recent advances in structural biology, nowadays three-dimensional structures of various proteins are solved on a routine basis. A large portion of these contain structural repetitions or internal symmetries. To understand the evolution mechanisms of these proteins and how structural repetitions affect the protein function, we need to be able to detect such proteins very robustly. As deep learning is particularly suited to deal with spatially organized data, we applied it to the detection of proteins with structural repetitions. Results: We present DeepSymmetry, a vers…
Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community. However, different from a natural language sentence, a program contains rich, explicit, and complicated structural information. Hence, traditional NLP models may be inappropriate for programs. In this paper, we propose a novel tree-based convolutional neural network (TBCNN) for programming language processing, in which a convolution kernel is designed over programs' abstract syntax t…
Queen Mary University of London（伦敦玛丽女王大学）；Institute for Research and Coordination in Acoustics/Music（声学/音乐研究与协调研究所）
The identification of structural differences between a music performance and the score is a challenging yet integral step of audio-to-score alignment, an important subtask of music information retrieval. We present a novel method to detect such differences between the score and performance for a given piece of music using progressively dilated convolutional neural networks. Our method incorporates varying dilation rates at different layers to capture both short-term and long-term context, and can be employed successfully in the presence of limited annotated data. We conduct experiments on audi…
