Artificial neural networks have been successfully used for many different classification tasks including malware detection and distinguishing between malicious and non-malicious programs. Although artificial neural networks perform very well on these tasks, they are also vulnerable to adversarial examples. An adversarial example is a sample that has minor modifications made to it so that the neural network misclassifies it. Many techniques have been proposed, both for crafting adversarial examples and for hardening neural networks against them. Most previous work has been done in the image domain. Some of the attacks have been adopted to work in the malware domain which typically deals with binary feature vectors. In order to better understand the space of adversarial examples in malware classification, we study different approaches of crafting adversarial examples and defense techniques in the malware domain and compare their effectiveness on multiple datasets.

This paper proposes interpretable image synthesis by learning hierarchical AND-OR networks of sparsely connected semantically meaningful nodes. The proposed method is based on the compositionality and interpretability of scene-objects-parts-subparts-primitives hierarchy in image representation. A scene has different types (i.e., OR) each of which consists of a number of objects (i.e., AND). This can be recursively formulated across the scene-objects-parts-subparts hierarchy and is terminated at the primitive level (e.g., Gabor wavelets-like basis). To realize this interpretable AND-OR hierarchy in image synthesis, the proposed method consists of two components: (i) Each layer of the hierarchy is represented by an over-completed set of basis functions. The basis functions are instantiated using convolution to be translation covariant. Off-the-shelf convolutional neural architectures are then exploited to implement the hierarchy. (ii) Sparsity-inducing constraints are introduced in end-to-end training, which facilitate a sparsely connected AND-OR network to emerge from initially densely connected convolutional neural networks. A straightforward sparsity-inducing constraint is utilized, that is to only allow the top-$k$ basis functions to be active at each layer (where $k$ is a hyperparameter). The learned basis functions are also capable of image reconstruction to explain away input images. In experiments, the proposed method is tested on five benchmark datasets. The results show that meaningful and interpretable hierarchical representations are learned with better qualities of image synthesis and reconstruction obtained than state-of-the-art baselines.

This paper presents a smart sliding Chinese pinyin Input Method Editor (IME) for touchscreen devices which allows user finger sliding from one key to another on the touchscreen instead of tapping keys one by one, while the target Chinese character sequence will be predicted during the sliding process to help user input Chinese characters efficiently. Moreover, the layout of the virtual keyboard of our IME adapts to user sliding for more efficient inputting. The layout adaption process is utilized with Recurrent Neural Networks (RNN) and deep reinforcement learning. The pinyin-to-character converter is implemented with a sequence-to-sequence (Seq2Seq) model to predict the target Chinese sequence. A sliding simulator is built to automatically produce sliding samples for model training and virtual keyboard test. The key advantage of our proposed IME is that nearly all its built-in tactics can be optimized automatically with deep learning algorithms only following user behavior. Empirical studies verify the effectiveness of the proposed model and show a better user input efficiency.

In computer chip manufacturing, the study of etch patterns on silicon wafers, or metrology, occurs on the nano-scale and is therefore subject to large variation from small, yet significant, perturbations in the manufacturing environment. An enormous amount of information can be gathered from a single etch process, a sequence of actions taken to produce an etched wafer from a blank piece of silicon. Each final wafer, however, is costly to take measurements from, which limits the number of examples available to train a predictive model. Part of the significance of this work is the success we saw from the models despite the limited number of examples. In order to accommodate the high dimensional process signatures, we isolated important sensor variables and applied domain-specific summarization on the data using multiple feature engineering techniques. We used a neural network architecture consisting of the summarized inputs, a single hidden layer of 4032 units, and an output layer of one unit. Two different models were learned, corresponding to the metrology measurements in the dataset, Recess and Remaining Mask. The outputs are related abstractly and do not form a two dimensional space, thus two separate models were learned. Our results approach the error tolerance of the microscopic imaging system. The model can make predictions for a class of etch recipes that include the correct number of etch steps and plasma reactors with the appropriate sensors, which are chambers containing an ionized gas that determine the manufacture environment. Notably, this method is not restricted to some maximum process length due to the summarization techniques used. This allows the method to be adapted to new processes that satisfy the aforementioned requirements. In order to automate semiconductor manufacturing, models like these will be needed throughout the process to evaluate production quality.

Antifreeze proteins (AFPs) are the sub-set of ice binding proteins indispensable for the species living in extreme cold weather. These proteins bind to the ice crystals, hindering their growth into large ice lattice that could cause physical damage. There are variety of AFPs found in numerous organisms and due to the heterogeneous sequence characteristics, AFPs are found to demonstrate a high degree of diversity, which makes their prediction a challenging task. Herein, we propose a machine learning framework to deal with this vigorous and diverse prediction problem using the manifolding learning through composition of k-spaced amino acid pairs. We propose to use the deep neural network with skipped connection and ReLU non-linearity to learn the non-linear mapping of protein sequence descriptor and class label. The proposed antifreeze protein prediction method called AFP-CKSAAP has shown to outperform the contemporary methods, achieving excellent prediction scores on standard dataset. The main evaluater for the performance of the proposed method in this study is Youden's index whose high value is dependent on both sensitivity and specificity. In particular, AFP-CKSAAP yields a Youden's index value of 0.82 on the independent dataset, which is better than previous methods.

Self-attentional models are a new paradigm for sequence modelling tasks which differ from common sequence modelling methods, such as recurrence-based and convolution-based sequence learning, in the way that their architecture is only based on the attention mechanism. Self-attentional models have been used in the creation of the state-of-the-art models in many NLP tasks such as neural machine translation, but their usage has not been explored for the task of training end-to- end task-oriented dialogue generation systems yet. In this study, we apply these models on the three different datasets for training task-oriented chatbots. Our finding shows that self-attentional models can be exploited to create end-to-end task-oriented chatbots which not only achieve higher evaluation scores compared to recurrence-based models, but also do so more efficiently.

We address the problem of combining sequence models of symbolic music with user defined constraints. For typical models this is nontrivial as only the conditional distribu - tion of each symbol given the earlier symbols is available, while the constraints correspond to arbitrary times. Previ - ously this has been addressed by assuming a discrete time model of fixed rhythm. We generalise to continuous time and arbitrary rhythm by introducing a simple, novel, and efficie nt particle filter scheme, applicable to general continuous ti me point processes. Extensive experimental evaluations demo n-strate that in comparison with a more traditional beam searc h baseline, the particle filter exhibits superior statistica l properties and yields more agreeable results in an extensive human listening test experiment.

Identifying and Resisting Adversarial Videos Using T emporal Consistency Xiaojun Jia 12, Xingxing Wei 1, Xiaochun Cao 12 1 Institute of Information Engineering, Chinese Academy of Sciences 2 Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen 518055, China 3 Beihang University Abstract Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this paper, we propose an effective defense framework to characterize and defend adversarial videos. The proposed method contains two phases: (1) adversarial video detection using temporal consistency between adjacent frames, and (2) adversarial perturbation reduction via denois-ers in the spatial and temporal domains respectively. Specifically, because of the linear nature of DNNs, the imperceptible perturbations will enlarge with the increasing of DNNs' depth, which leads to the inconsistency of DNNs' output between adjacent frames. However, the benign video frames often have the same outputs with their neighbor frames owing to the slight changes. Based on this observation, we can distinguish between adversarial videos and benign videos. After that, we utilize different defense strategies against different attacks. We propose the temporal defense, which reconstructs the polluted frames with their temporally neighbor clean frames, to deal with the adversarial videos with sparse polluted frames. For the videos with dense polluted frames, we use an efficient adversarial denoiser to process each frame in the spatial domain, and thus purify the perturbations (we call it as spatial defense). A series of experiments conducted on the UCF-101 dataset demonstrate that the proposed method significantly improves the robustness of video classifiers against adversarial attacks. Introduction With the rapid growth of video data on the internet, automatic video classification (Karpathy et al. 2014a) is becoming more and more important. Specifically, this task includes action recognition (Y ue-Hei Ng et al. 2015), scene classification (Huang et al. 1999), object classification (Zhang et al. 2007) and so on.

We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for recommender systems with large-scale dynamic sparse features. Our framework achieves faster convergence with less communication overhead and better computing resource utilization. DES strategy splits a weights-rich operator into sub-operators with co-located weights and aggregates partial results with much smaller communication cost to form a computationally equivalent substitution to the original operator. We show that for different types of models that recommender systems use, we can always find computational equivalent substitutions and splitting strategies for their weights-rich operators with theoretical communication load reduced ranging from 72.26% to 99.77%. We also present an implementation of DES that outperforms state-of-the-art recommender systems. Experiments show that our framework achieves up to 83% communication savings compared to other recommender systems, and can bring up to 4.5x improvement on throughput for deep models.

Deep neural networks have introduced novel and useful tools to the machine learning community, and other types of classifiers can make use of these tools to improve their performance and generality. This paper reviews the current state of the art for deep learning classifier technologies that are being used outside of deep neural networks. Many components of existing deep neural network architectures can be employed by non-network classifiers. In this paper, we review the feature learning, optimization, and regularization methods that form a core of deep network technologies. We then survey non-neural network learning algorithms that make innovative use of these methods to improve classification. We conclude by discussing directions that can be pursued to expand the area of deep learning for a variety of classification algorithms.