January 26, 2020

3153 words 15 mins read

Paper Group ANR 1501

Relative rationality: Is machine rationality subjective?. FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation. Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things. Reframing Threat Detection: Inside esINSIDER. Deep Variational Semi-Supervised Novelty Detection. Deep Generative Models Strike Back! Improvin …

Relative rationality: Is machine rationality subjective?


Title	Relative rationality: Is machine rationality subjective?
Authors	Tshilidzi Marwala
Abstract	Rational decision making in its linguistic description means making logical decisions. In essence, a rational agent optimally processes all relevant information to achieve its goal. Rationality has two elements and these are the use of relevant information and the efficient processing of such information. In reality, relevant information is incomplete, imperfect and the processing engine, which is a brain for humans, is suboptimal. Humans are risk averse rather than utility maximizers. In the real world, problems are predominantly non-convex and this makes the idea of rational decision-making fundamentally unachievable and Herbert Simon called this bounded rationality. There is a trade-off between the amount of information used for decision-making and the complexity of the decision model used. This explores whether machine rationality is subjective and concludes that indeed it is.
Tasks	Decision Making
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04832v1
PDF	http://arxiv.org/pdf/1902.04832v1.pdf
PWC	https://paperswithcode.com/paper/relative-rationality-is-machine-rationality
Repo
Framework

FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation


Title	FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
Authors	Zirui Wang, Shuda Li, Henry Howard-Jenkins, Victor Adrian Prisacariu, Min Chen
Abstract	We present FlowNet3D++, a deep scene flow estimation network. Inspired by classical methods, FlowNet3D++ incorporates geometric constraints in the form of point-to-plane distance and angular alignment between individual vectors in the flow field, into FlowNet3D. We demonstrate that the addition of these geometric loss terms improves the previous state-of-art FlowNet3D accuracy from 57.85% to 63.43%. To further demonstrate the effectiveness of our geometric constraints, we propose a benchmark for flow estimation on the task of dynamic 3D reconstruction, thus providing a more holistic and practical measure of performance than the breakdown of individual metrics previously used to evaluate scene flow. This is made possible through the contribution of a novel pipeline to integrate point-based scene flow predictions into a global dense volume. FlowNet3D++ achieves up to a 15.0% reduction in reconstruction error over FlowNet3D, and up to a 35.2% improvement over KillingFusion alone. We will release our scene flow estimation code later.
Tasks	3D Reconstruction, Scene Flow Estimation
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01438v2
PDF	https://arxiv.org/pdf/1912.01438v2.pdf
PWC	https://paperswithcode.com/paper/flownet3d-geometric-losses-for-deep-scene
Repo
Framework

Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things


Title	Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things
Authors	Maede Zolanvari, Marcio A. Teixeira, Lav Gupta, Khaled M. Khan, Raj Jain
Abstract	It is critical to secure the Industrial Internet of Things (IIoT) devices because of potentially devastating consequences in case of an attack. Machine learning and big data analytics are the two powerful leverages for analyzing and securing the Internet of Things (IoT) technology. By extension, these techniques can help improve the security of the IIoT systems as well. In this paper, we first present common IIoT protocols and their associated vulnerabilities. Then, we run a cyber-vulnerability assessment and discuss the utilization of machine learning in countering these susceptibilities. Following that, a literature review of the available intrusion detection solutions using machine learning models is presented. Finally, we discuss our case study, which includes details of a real-world testbed that we have built to conduct cyber-attacks and to design an intrusion detection system (IDS). We deploy backdoor, command injection, and Structured Query Language (SQL) injection attacks against the system and demonstrate how a machine learning based anomaly detection system can perform well in detecting these attacks. We have evaluated the performance through representative metrics to have a fair point of view on the effectiveness of the methods.
Tasks	Anomaly Detection, Intrusion Detection
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05771v1
PDF	https://arxiv.org/pdf/1911.05771v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-network-vulnerability
Repo
Framework

Reframing Threat Detection: Inside esINSIDER


Title	Reframing Threat Detection: Inside esINSIDER
Authors	M. Arthur Munson, Jason Kichen, Dustin Hillard, Ashley Fidler, Peiter Zatko
Abstract	We describe the motivation and design for esINSIDER, an automated tool that detects potential persistent and insider threats in a network. esINSIDER aggregates clues from log data, over extended time periods, and proposes a small number of cases for human experts to review. The proposed cases package together related information so the analyst can see a bigger picture of what is happening, and their evidence includes internal network activity resembling reconnaissance and data collection. The core ideas are to 1) detect fundamental campaign behaviors by following data movements over extended time periods, 2) link together behaviors associated with different meta-goals, and 3) use machine learning to understand what activities are expected and consistent for each individual network. We call this approach campaign analytics because it focuses on the threat actor’s campaign goals and the intrinsic steps to achieve them. Linking different campaign behaviors (internal reconnaissance, collection, exfiltration) reduces false positives from business-as-usual activities and creates opportunities to detect threats before a large exfiltration occurs. Machine learning makes it practical to deploy this approach by reducing the amount of tuning needed.
Tasks
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03584v1
PDF	http://arxiv.org/pdf/1904.03584v1.pdf
PWC	https://paperswithcode.com/paper/reframing-threat-detection-inside-esinsider
Repo
Framework

Deep Variational Semi-Supervised Novelty Detection


Title	Deep Variational Semi-Supervised Novelty Detection
Authors	Tal Daniel, Thanard Kurutach, Aviv Tamar
Abstract	In anomaly detection (AD), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generative models, such as variational autoencoders (VAEs), for unsupervised learning of the normal data distribution. In semi-supervised AD (SSAD), the data also includes a small sample of labeled anomalies. In this work, we propose two variational methods for training VAEs for SSAD. The intuitive idea in both methods is to train the encoder to `separate’ between latent vectors for normal and outlier data. We show that this idea can be derived from principled probabilistic formulations of the problem, and propose simple and effective algorithms. Our methods can be applied to various data types, as we demonstrate on SSAD datasets ranging from natural images to astronomy and medicine, and can be combined with any VAE model architecture. When comparing to state-of-the-art SSAD methods that are not specific to particular data types, we obtain marked improvement in outlier detection. \|
Tasks	Anomaly Detection, Outlier Detection
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04971v1
PDF	https://arxiv.org/pdf/1911.04971v1.pdf
PWC	https://paperswithcode.com/paper/deep-variational-semi-supervised-novelty-1
Repo
Framework

Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data


Title	Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
Authors	John Just, Sambuddha Ghosal
Abstract	Advances in deep generative and density models have shown impressive capacity to model complex probability density functions in lower-dimensional space. Also, applying such models to high-dimensional image data to model the PDF has shown poor generalization, with out-of-distribution data being assigned equal or higher likelihood than in-sample data. Methods to deal with this have been proposed that deviate from a fully unsupervised approach, requiring large ensembles or additional knowledge about the data, not commonly available in the real-world. In this work, the previously offered reasoning behind these issues is challenged empirically, and it is shown that data-sets such as MNIST fashion/digits and CIFAR10/SVHN are trivially separable and have no overlap on their respective data manifolds that explains the higher OoD likelihood. Models like masked autoregressive flows and block neural autoregressive flows are shown to not suffer from OoD likelihood issues to the extent of GLOW, PixelCNN++, and real NVP. A new avenue is also explored which involves a change of basis to a new space of the same dimension with an orthonormal unitary basis of eigenvectors before modeling. In the test data-sets and models, this aids in pushing down the relative likelihood of the contrastive OoD data set and improve discrimination results. The significance of the density of the original space is maintained, while invertibility remains tractable. Finally, a look to the previous generation of generative models in the form of probabilistic principal component analysis is inspired, and revisited for the same data-sets and shown to work really well for discriminating anomalies based on likelihood in a fully unsupervised fashion compared with pixelCNN++, GLOW, and real NVP with less complexity and faster training. Also, dimensionality reduction using PCA is shown to improve anomaly detection in generative models.
Tasks	Anomaly Detection, Dimensionality Reduction
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04699v1
PDF	https://arxiv.org/pdf/1911.04699v1.pdf
PWC	https://paperswithcode.com/paper/deep-generative-models-strike-back-improving
Repo
Framework

Deep Online Learning with Stochastic Constraints


Title	Deep Online Learning with Stochastic Constraints
Authors	Guy Uziel
Abstract	Deep learning models are considered to be state-of-the-art in many offline machine learning tasks. However, many of the techniques developed are not suitable for online learning tasks. The problem of using deep learning models with sequential data becomes even harder when several loss functions need to be considered simultaneously, as in many real-world applications. In this paper, we, therefore, propose a novel online deep learning training procedure which can be used regardless of the neural network’s architecture, aiming to deal with the multiple objectives case. We demonstrate and show the effectiveness of our algorithm on the Neyman-Pearson classification problem on several benchmark datasets.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10817v1
PDF	https://arxiv.org/pdf/1905.10817v1.pdf
PWC	https://paperswithcode.com/paper/deep-online-learning-with-stochastic
Repo
Framework

PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds


Title	PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
Authors	Wenxuan Wu, Zhiyuan Wang, Zhuwen Li, Wei Liu, Li Fuxin
Abstract	We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion. Flow computed at the coarse level is upsampled and warped to a finer level, enabling the algorithm to accommodate for large motion without a prohibitive search space. We introduce novel cost volume, upsampling, and warping layers to efficiently handle 3D point cloud data. Unlike traditional cost volumes that require exhaustively computing all the cost values on a high-dimensional grid, our point-based formulation discretizes the cost volume onto input 3D points, and a PointConv operation efficiently computes convolutions on the cost volume. Experiment results on FlyingThings3D outperform the state-of-the-art by a large margin. We further explore novel self-supervised losses to train our model and achieve comparable results to state-of-the-art trained with supervised loss. Without any fine-tuning, our method also shows great generalization ability on KITTI Scene Flow 2015 dataset, outperforming all previous methods.
Tasks	Scene Flow Estimation
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12408v1
PDF	https://arxiv.org/pdf/1911.12408v1.pdf
PWC	https://paperswithcode.com/paper/pointpwc-net-a-coarse-to-fine-network-for
Repo
Framework

Paraphrasing with Large Language Models


Title	Paraphrasing with Large Language Models
Authors	Sam Witteveen, Martin Andrews
Abstract	Recently, large language models such as GPT-2 have shown themselves to be extremely adept at text generation and have also been able to achieve high-quality results in many downstream NLP tasks such as text classification, sentiment analysis and question answering with the aid of fine-tuning. We present a useful technique for using a large language model to perform the task of paraphrasing on a variety of texts and subjects. Our approach is demonstrated to be capable of generating paraphrases not only at a sentence level but also for longer spans of text such as paragraphs without needing to break the text into smaller chunks.
Tasks	Language Modelling, Question Answering, Sentiment Analysis, Text Classification, Text Generation
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09661v1
PDF	https://arxiv.org/pdf/1911.09661v1.pdf
PWC	https://paperswithcode.com/paper/paraphrasing-with-large-language-models-1
Repo
Framework

A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithm


Title	A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithm
Authors	Xiaolei Liu, Yuheng Luo, Xiaosong Zhang, Qingxin Zhu
Abstract	Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of the generation approaches either assume that the attacker has full knowledge of the neural network model or are limited by the type of attacked model. In this paper, we propose a new approach that generates a black-box attack to neural networks based on the swarm evolutionary algorithm. Benefiting from the improvements in the technology and theoretical characteristics of evolutionary algorithms, our approach has the advantages of effectiveness, black-box attack, generality, and randomness. Our experimental results show that both the MNIST images and the CIFAR-10 images can be perturbed to successful generate a black-box attack with 100% probability on average. In addition, the proposed attack, which is successful on distilled neural networks with almost 100% probability, is resistant to defensive distillation. The experimental results also indicate that the robustness of the artificial intelligence algorithm is related to the complexity of the model and the data set. In addition, we find that the adversarial samples to some extent reproduce the characteristics of the sample data learned by the neural network model.
Tasks
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09892v1
PDF	http://arxiv.org/pdf/1901.09892v1.pdf
PWC	https://paperswithcode.com/paper/a-black-box-attack-on-neural-networks-based
Repo
Framework

Robust Data Association for Object-level Semantic SLAM


Title	Robust Data Association for Object-level Semantic SLAM
Authors	Xueyang Kang, Shunying Yuan
Abstract	Simultaneous mapping and localization (SLAM) in an real indoor environment is still a challenging task. Traditional SLAM approaches rely heavily on low-level geometric constraints like corners or lines, which may lead to tracking failure in textureless surroundings or cluttered world with dynamic objects. In this paper, a compact semantic SLAM framework is proposed, with utilization of both geometric and object-level semantic constraints jointly, a more consistent mapping result, and more accurate pose estimation can be obtained. Two main contributions are presented int the paper, a) a robust and efficient SLAM data association and optimization framework is proposed, it models both discrete semantic labeling and continuous pose. b) a compact map representation, combining 2D Lidar map with object detection is presented. Experiments on public indoor datasets, TUM-RGBD, ICL-NUIM, and our own collected datasets prove the improving of SLAM robustness and accuracy compared to other popular SLAM systems, meanwhile a map maintenance efficiency can be achieved.
Tasks	Object Detection, Pose Estimation
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13493v1
PDF	https://arxiv.org/pdf/1909.13493v1.pdf
PWC	https://paperswithcode.com/paper/robust-data-association-for-object-level
Repo
Framework

A characterisation of S-box fitness landscapes in cryptography


Title	A characterisation of S-box fitness landscapes in cryptography
Authors	Domagoj Jakobovic, Stjepan Picek, Marcella S. R. Martins, Markus Wagner
Abstract	Substitution Boxes (S-boxes) are nonlinear objects often used in the design of cryptographic algorithms. The design of high quality S-boxes is an interesting problem that attracts a lot of attention. Many attempts have been made in recent years to use heuristics to design S-boxes, but the results were often far from the previously known best obtained ones. Unfortunately, most of the effort went into exploring different algorithms and fitness functions while little attention has been given to the understanding why this problem is so difficult for heuristics. In this paper, we conduct a fitness landscape analysis to better understand why this problem can be difficult. Among other, we find that almost each initial starting point has its own local optimum, even though the networks are highly interconnected.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04724v1
PDF	http://arxiv.org/pdf/1902.04724v1.pdf
PWC	https://paperswithcode.com/paper/a-characterisation-of-s-box-fitness
Repo
Framework

A visual encoding model based on deep neural networks and transfer learning


Title	A visual encoding model based on deep neural networks and transfer learning
Authors	Chi Zhang, Kai Qiao, Linyuan Wang, Li Tong, Guoen Hu, Ruyuan Zhang, Bin Yan
Abstract	Background: Building visual encoding models to accurately predict visual responses is a central challenge for current vision-based brain-machine interface techniques. To achieve high prediction accuracy on neural signals, visual encoding models should include precise visual features and appropriate prediction algorithms. Most existing visual encoding models employ hand-craft visual features (e.g., Gabor wavelets or semantic labels) or data-driven features (e.g., features extracted from deep neural networks (DNN)). They also assume a linear mapping between feature representation to brain activity. However, it remains unknown whether such linear mapping is sufficient for maximizing prediction accuracy. New Method: We construct a new visual encoding framework to predict cortical responses in a benchmark functional magnetic resonance imaging (fMRI) dataset. In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i.e., AlexNet) and train a nonlinear mapping from visual features to brain activity. This nonlinear mapping replaces the conventional linear mapping and is supposed to improve prediction accuracy on brain activity. Results: The proposed framework can significantly predict responses of over 20% voxels in early visual areas (i.e., V1-lateral occipital region, LO) and achieve unprecedented prediction accuracy. Comparison with Existing Methods: Comparing to two conventional visual encoding models, we find that the proposed encoding model shows consistent higher prediction accuracy in all early visual areas, especially in relatively anterior visual areas (i.e., V4 and LO). Conclusions: Our work proposes a new framework to utilize pre-trained visual features and train non-linear mappings from visual features to brain activity.
Tasks	Transfer Learning
Published	2019-02-23
URL	http://arxiv.org/abs/1902.08793v1
PDF	http://arxiv.org/pdf/1902.08793v1.pdf
PWC	https://paperswithcode.com/paper/a-visual-encoding-model-based-on-deep-neural
Repo
Framework

Deep Learning versus Traditional Classifiers on Vietnamese Students’ Feedback Corpus


Title	Deep Learning versus Traditional Classifiers on Vietnamese Students’ Feedback Corpus
Authors	Phu X. V. Nguyen, Tham T. T. Hong, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Abstract	Student’s feedback is an important source of collecting students’ opinions to improve the quality of training activities. Implementing sentiment analysis into student feedback data, we can determine sentiments polarities which express all problems in the institution since changes necessary will be applied to improve the quality of teaching and learning. This study focused on machine learning and natural language processing techniques (NaiveBayes, Maximum Entropy, Long Short-Term Memory, Bi-Directional Long Short-Term Memory) on the VietnameseStudents’ Feedback Corpus collected from a university. The final results were compared and evaluated to find the most effective model based on different evaluation criteria. The experimental results show that the Bi-Directional LongShort-Term Memory algorithm outperformed than three other algorithms in terms of the F1-score measurement with 92.0% on the sentiment classification task and 89.6% on the topic classification task. In addition, we developed a sentiment analysis application analyzing student feedback. The application will help the institution to recognize students’ opinions about a problem and identify shortcomings that still exist. With the use of this application, the institution can propose an appropriate method to improve the quality of training activities in the future.
Tasks	Sentiment Analysis
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07223v1
PDF	https://arxiv.org/pdf/1911.07223v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-versus-traditional-classifiers
Repo
Framework

Error Resilient Deep Compressive Sensing


Title	Error Resilient Deep Compressive Sensing
Authors	Thuong, Nguyen Canh, Chien, Trinh Van
Abstract	Compressive sensing (CS) is an emerging sampling technology that enables reconstructing signals from a subset of measurements and even corrupted measurements. Deep learning-based compressive sensing (DCS) has improved CS performance while maintaining a fast reconstruction but requires a training network for each measurement rate. Also, concerning the transmission scheme of measurement lost, DCS cannot recover the original signal. Thereby, it fails to maintain the error-resilient property. In this work, we proposed a robust deep reconstruction network to preserve the error-resilient property under the assumption of random measurement lost. Measurement lost layer is proposed to simulate the measurement lost in an end-to-end framework.
Tasks	Compressive Sensing
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12507v1
PDF	https://arxiv.org/pdf/1911.12507v1.pdf
PWC	https://paperswithcode.com/paper/error-resilient-deep-compressive-sensing
Repo
Framework