1,721,307 research outputs found
A Multiscale Graph Convolutional Network Using Hierarchical Clustering
Full text linkThe information contained in hierarchical topology, intrinsic to many networks, is currently underutilised. A novel architecture is explored which exploits this information through a multiscale decomposition. A dendrogram is produced by a Girvan-Newman hierarchical clustering algorithm. It is segmented and fed through graph convolutional layers, allowing the architecture to learn multiple scale latent space representations of the network, from fine to coarse grained. The architecture is tested on a benchmark citation network, demonstrating competitive performance. Given the abundance of hierarchical networks, possible applications include quantum molecular property prediction, protein interface prediction and multiscale computational substrates for partial differential equations
International Workshop on Application of Intelligent Technology in Security - AITS 2021
Full text linkOn behalf of the Organizing Committee, it is our pleasure to welcome you to the International Workshop on Application of Intelligent Technology in Security (AITS). AITS workshop will be held in conjunction with the 51th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) on 21 June 2021
An Effective Loss Function for Generating 3D Models from Single 2D Image Without Rendering
Full text linkDifferentiable rendering is a very successful technique that applies to a Single-View 3D Reconstruction. Current renderers use losses based on pixels between a rendered image of some 3D reconstructed object and ground-truth images from given matched viewpoints to optimise parameters of the 3D shape. These models require a rendering step, along with visibility handling and evaluation of the shading model. The main goal of this paper is to demonstrate that we can avoid these steps and still get reconstruction results as other state-of-the-art models that are equal or even better than existing category-specific reconstruction methods. First, we use the same CNN architecture for the prediction of a point cloud shape and pose prediction like the one used by Insafutdinov & Dosovitskiy. Secondly, we propose the novel effective loss function that evaluates how well the projections of reconstructed 3D point clouds cover the ground-truth object’s silhouette. Then we use Poisson Surface Reconstruction to transform the reconstructed point cloud into a 3D mesh. Finally, we perform a GAN-based texture mapping on a particular 3D mesh and produce a textured 3D mesh from a single 2D image. We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time
Dynamic neural network channel execution for efficient training
No full textExisting methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and number of computing operations required for training and inference. Our framework efficiently integrates pruning as part of the training procedure by exploring and tracking the relative importance of convolutional channels. At each training step, we select only a subset of highly salient channels to execute according to the combinatorial upper confidence bound algorithm, and run a forward and backward pass only on these activated channels, hence learning their parameters. Consequently, we enable the efficient discovery of compact models. We validate our approach empirically on state-of-the-art CNNs - VGGNet, ResNet and DenseNet, and on several image classification datasets. Results demonstrate our framework for dynamic channel execution reduces computational cost up to 4× and parameter count up to 9×, thus reducing the memory and computational demands for discovering and training compact neural network models
Robust android malware detection based on subgraph network and denoising GCN network
No full textThis paper proposes an Android malware detection model based on Android Function Call Graph (FCG) and Denoising Graph Convolutional Neural Network. This study proposes a method to simplify the FCG to reduce its size, and a new method to construct vertex feature vectors. The model uses the subgraph network to detect the underlying structural features of the FCG and discover the confusion attack. A denoising graph neural network is applied to graph convolution to reduce the impact of obfuscation attacks
XFlow: Cross-Modal Deep Neural Networks for Audiovisual Classification
Full text linkIn recent years, there have been numerous developments toward solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for example, correlations in the space or time domain across modalities - but should be wisely exploited in order to benefit from their full predictive potential. We propose two deep learning architectures with multimodal cross connections that allow for dataflow between several feature extractors (XFlow). Our models derive more interpretable features and achieve better performances than models that do not exchange representations, usefully exploiting correlations between audio and visual data, which have a different dimensionality and are nontrivially exchangeable. This article improves on the existing multimodal deep learning algorithms in two essential ways: 1) it presents a novel method for performing cross modality (before features are learned from individual modalities) and 2) extends the previously proposed cross connections that only transfer information between the streams that process compatible data. Illustrating some of the representations learned by the connections, we analyze their contribution to the increase in discrimination ability and reveal their compatibility with a lip-reading network intermediate representation. We provide the research community with Digits, a new data set consisting of three data types extracted from videos of people saying the digits 0-9. Results show that both cross-modal architectures outperform their baselines (by up to 11.5%) when evaluated on the AVletters, CUAVE, and Digits data sets, achieving the state-of-the-art results
Dynamic survival prediction in intensive care units from heterogeneous time series without the need for variable selection or curation
Full text linkExtensive monitoring in intensive care units (ICUs) generates large quantities of data which contain numerous trends that are difficult for clinicians to systematically evaluate. Current approaches to such heterogeneity in electronic health records (EHRs) discard pertinent information. We present a deep learning pipeline that uses all uncurated chart, lab, and output events for prediction of in-hospital mortality without variable selection. Over 21,000 ICU patients and tens of thousands of variables derived from the MIMIC-III database were used to train and validate our model. Recordings in the first few hours of a patient’s stay were found to be strongly predictive of mortality, outperforming models using SAPS II and OASIS scores, AUROC 0.72 and 0.76 at 24 h respectively, within just 12 h of ICU admission. Our model achieves a very strong predictive performance of AUROC 0.85 (95% CI 0.83–0.86) after 48 h. Predictive performance increases over the first 48 h, but suffers from diminishing returns, providing rationale for time-limited trials of critical care and suggesting that the timing of decision making can be optimised and individualised
Poster: CFMAP: A Robust CPU Clock Fingerprint Model for Device Authentication
No full textThe internal clock of the CPU uses oscillators made from quartz crystals. Small changes in these crystals can cause small but measurable differences in the clock frequency. Under a low CPU load, the function execution time distribution follows the Pareto distribution. However, the function execution time distribution no longer follows the Pareto distribution when the CPU load is high, and the CPU clock fingerprint becomes invalid. In view of this problem, this paper proposes an adaptive Pareto principle that adaptively adjusts the distribution according to the CPU load. Based on this, the robust CPU Clock Fingerprint Model based on the Adaptive Pareto Principle (CFMAP) is proposed. Via a KNN-based fingerprint recognition method, CFMAP solves the instability of existing CPU clock fingerprints under a high CPU load. Experiments show that the average recognition rate of CFMAP fingerprints is 96.82%. Moreover, they are highly robust against CPU load attacks and virtual machine attacks
GAT-DNS: DNS Multivariate Time Series Prediction Model Based on Graph Attention Network
No full textAs one of the most basic services of the Internet, DNS has suffered a lot of attacks. Existing attack detection methods rely on the learning of malicious samples, so it is difficult to detect new attacks and long-period attacks. This paper transforms the DNS data flow into time series, and proposes a DNS anomaly detection method based on graph attention network and graph embedding (GAT-DNS). GAT-DNS establishes a multivariate time series model to depict the DNS service status. When the actual flow of a feature exceeds the predicted range, it is considered that abnormal DNS behavior is found. In this paper, vertex dependency is proposed to describe the dependency between features. The features with high vertex dependency values are deleted to achieve model compression. This improves the system efficiency. Experiments on open data sets show that compared with the latest AD-Bop and QLAD methods, GAT-DNS method not only improves the precision, recall and F1 value, but also improves the time efficiency of the model
- …
