May 7, 2019

2674 words 13 mins read

Paper Group ANR 49

Adversarial Perturbations Against Deep Neural Networks for Malware Classification. Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research. Learning to SMILE(S). The Physical Systems Behind Optimization Algorithms. Extracting Formal Models from Normative Texts. Continuum directions for supervised dimension reduction. …

Adversarial Perturbations Against Deep Neural Networks for Malware Classification


Title	Adversarial Perturbations Against Deep Neural Networks for Malware Classification
Authors	Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, Patrick McDaniel
Abstract	Deep neural networks, like many other machine learning models, have recently been shown to lack robustness against adversarially crafted inputs. These inputs are derived from regular inputs by minor yet carefully selected perturbations that deceive machine learning models into desired misclassifications. Existing work in this emerging field was largely specific to the domain of image classification, since the high-entropy of images can be conveniently manipulated without changing the images’ overall visual appearance. Yet, it remains unclear how such attacks translate to more security-sensitive applications such as malware detection - which may pose significant challenges in sample generation and arguably grave consequences for failure. In this paper, we show how to construct highly-effective adversarial sample crafting attacks for neural networks used as malware classifiers. The application domain of malware classification introduces additional constraints in the adversarial sample crafting problem when compared to the computer vision domain: (i) continuous, differentiable input domains are replaced by discrete, often binary inputs; and (ii) the loose condition of leaving visual appearance unchanged is replaced by requiring equivalent functional behavior. We demonstrate the feasibility of these attacks on many different instances of malware classifiers that we trained using the DREBIN Android malware data set. We furthermore evaluate to which extent potential defensive mechanisms against adversarial crafting can be leveraged to the setting of malware classification. While feature reduction did not prove to have a positive impact, distillation and re-training on adversarially crafted samples show promising results.
Tasks	Image Classification, Malware Classification, Malware Detection
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04435v2
PDF	http://arxiv.org/pdf/1606.04435v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-perturbations-against-deep-neural
Repo
Framework

Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research


Title	Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
Authors	Douwe Kiela, Luana Bulat, Anita L. Vero, Stephen Clark
Abstract	Meaning has been called the “holy grail” of a variety of scientific disciplines, ranging from linguistics to philosophy, psychology and the neurosciences. The field of Artifical Intelligence (AI) is very much a part of that list: the development of sophisticated natural language semantics is a sine qua non for achieving a level of intelligence comparable to humans. Embodiment theories in cognitive science hold that human semantic representation depends on sensori-motor experience; the abundant evidence that human meaning representation is grounded in the perception of physical reality leads to the conclusion that meaning must depend on a fusion of multiple (perceptual) modalities. Despite this, AI research in general, and its subdisciplines such as computational linguistics and computer vision in particular, have focused primarily on tasks that involve a single modality. Here, we propose virtual embodiment as an alternative, long-term strategy for AI research that is multi-modal in nature and that allows for the kind of scalability required to develop the field coherently and incrementally, in an ethically responsible fashion.
Tasks
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07432v1
PDF	http://arxiv.org/pdf/1610.07432v1.pdf
PWC	https://paperswithcode.com/paper/virtual-embodiment-a-scalable-long-term
Repo
Framework

Learning to SMILE(S)


Title	Learning to SMILE(S)
Authors	Stanisław Jastrzębski, Damian Leśniak, Wojciech Marian Czarnecki
Abstract	This paper shows how one can directly apply natural language processing (NLP) methods to classification problems in cheminformatics. Connection between these seemingly separate fields is shown by considering standard textual representation of compound, SMILES. The problem of activity prediction against a target protein is considered, which is a crucial part of computer aided drug design process. Conducted experiments show that this way one can not only outrank state of the art results of hand crafted representations but also gets direct structural insights into the way decisions are made.
Tasks	Activity Prediction
Published	2016-02-19
URL	http://arxiv.org/abs/1602.06289v2
PDF	http://arxiv.org/pdf/1602.06289v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-smiles
Repo
Framework

The Physical Systems Behind Optimization Algorithms


Title	The Physical Systems Behind Optimization Algorithms
Authors	Lin F. Yang, R. Arora, V. Braverman, Tuo Zhao
Abstract	We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton’s methods as well as their Nesterov’s accelerated variants in a unified framework motivated by a natural connection of optimization algorithms to physical systems. Our analysis is applicable to more general algorithms and optimization problems {\it \textbf{beyond}} convexity and strong convexity, e.g. Polyak-\L ojasiewicz and error bound conditions (possibly nonconvex).
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02803v5
PDF	http://arxiv.org/pdf/1612.02803v5.pdf
PWC	https://paperswithcode.com/paper/the-physical-systems-behind-optimization
Repo
Framework

Extracting Formal Models from Normative Texts


Title	Extracting Formal Models from Normative Texts
Authors	John J. Camilleri, Normunds Gruzitis, Gerardo Schneider
Abstract	Normative texts are documents based on the deontic notions of obligation, permission, and prohibition. Our goal is to model such texts using the C-O Diagram formalism, making them amenable to formal analysis, in particular verifying that a text satisfies properties concerning causality of actions and timing constraints. We present an experimental, semi-automatic aid to bridge the gap between a normative text and its formal representation. Our approach uses dependency trees combined with our own rules and heuristics for extracting the relevant components. The resulting tabular data can then be converted into a C-O Diagram.
Tasks
Published	2016-07-06
URL	http://arxiv.org/abs/1607.01485v1
PDF	http://arxiv.org/pdf/1607.01485v1.pdf
PWC	https://paperswithcode.com/paper/extracting-formal-models-from-normative-texts
Repo
Framework

Continuum directions for supervised dimension reduction


Title	Continuum directions for supervised dimension reduction
Authors	Sungkyu Jung
Abstract	Dimension reduction of multivariate data supervised by auxiliary information is considered. A series of basis for dimension reduction is obtained as minimizers of a novel criterion. The proposed method is akin to continuum regression, and the resulting basis is called continuum directions. With a presence of binary supervision data, these directions continuously bridge the principal component, mean difference and linear discriminant directions, thus ranging from unsupervised to fully supervised dimension reduction. High-dimensional asymptotic studies of continuum directions for binary supervision reveal several interesting facts. The conditions under which the sample continuum directions are inconsistent, but their classification performance is good, are specified. While the proposed method can be directly used for binary and multi-category classification, its generalizations to incorporate any form of auxiliary data are also presented. The proposed method enjoys fast computation, and the performance is better or on par with more computer-intensive alternatives.
Tasks	Dimensionality Reduction
Published	2016-06-20
URL	http://arxiv.org/abs/1606.05988v3
PDF	http://arxiv.org/pdf/1606.05988v3.pdf
PWC	https://paperswithcode.com/paper/continuum-directions-for-supervised-dimension
Repo
Framework

Nesterov’s Accelerated Gradient and Momentum as approximations to Regularised Update Descent


Title	Nesterov’s Accelerated Gradient and Momentum as approximations to Regularised Update Descent
Authors	Aleksandar Botev, Guy Lever, David Barber
Abstract	We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov’s accelerated gradient method, lending a new intuitive interpretation to the latter algorithm. We show that a new algorithm, which we term Regularised Gradient Descent, can converge more quickly than either Nesterov’s algorithm or the classical momentum algorithm.
Tasks
Published	2016-07-07
URL	http://arxiv.org/abs/1607.01981v2
PDF	http://arxiv.org/pdf/1607.01981v2.pdf
PWC	https://paperswithcode.com/paper/nesterovs-accelerated-gradient-and-momentum
Repo
Framework

Reasoning About Pragmatics with Neural Listeners and Speakers


Title	Reasoning About Pragmatics with Neural Listeners and Speakers
Authors	Jacob Andreas, Dan Klein
Abstract	We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a simple feature-driven architecture (here a pair of neural “listener” and “speaker” models) to ground language in the world. Like inference-driven approaches to pragmatics, our model actively reasons about listener behavior when selecting utterances. For training, our approach requires only ordinary captions, annotated without demonstration of the pragmatic behavior the model ultimately exhibits. In human evaluations on a referring expression game, our approach succeeds 81% of the time, compared to a 69% success rate using existing techniques.
Tasks	Text Generation
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00562v2
PDF	http://arxiv.org/pdf/1604.00562v2.pdf
PWC	https://paperswithcode.com/paper/reasoning-about-pragmatics-with-neural
Repo
Framework

A Two-Phase Approach Towards Identifying Argument Structure in Natural Language


Title	A Two-Phase Approach Towards Identifying Argument Structure in Natural Language
Authors	Arkanath Pathak, Pawan Goyal, Plaban Bhowmick
Abstract	We propose a new approach for extracting argument structure from natural language texts that contain an underlying argument. Our approach comprises of two phases: Score Assignment and Structure Prediction. The Score Assignment phase trains models to classify relations between argument units (Support, Attack or Neutral). To that end, different training strategies have been explored. We identify different linguistic and lexical features for training the classifiers. Through ablation study, we observe that our novel use of word-embedding features is most effective for this task. The Structure Prediction phase makes use of the scores from the Score Assignment phase to arrive at the optimal structure. We perform experiments on three argumentation datasets, namely, AraucariaDB, Debatepedia and Wikipedia. We also propose two baselines and observe that the proposed approach outperforms baseline systems for the final task of Structure Prediction.
Tasks
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05420v1
PDF	http://arxiv.org/pdf/1612.05420v1.pdf
PWC	https://paperswithcode.com/paper/a-two-phase-approach-towards-identifying
Repo
Framework

Detection under Privileged Information


Title	Detection under Privileged Information
Authors	Z. Berkay Celik, Patrick McDaniel, Rauf Izmailov, Nicolas Papernot, Ryan Sheatsley, Raquel Alvarez, Ananthram Swami
Abstract	For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed malicious or non-malicious based on its similarity to the learned model at runtime. However, the training of the models has been historically limited to only those features available at runtime. In this paper, we consider an alternate learning approach that trains models using “privileged” information–features available at training time but not at runtime–to improve the accuracy and resilience of detection systems. In particular, we adapt and extend recent advances in knowledge transfer, model influence, and distillation to enable the use of forensic or other data unavailable at runtime in a range of security domains. An empirical evaluation shows that privileged information increases precision and recall over a system with no privileged information: we observe up to 7.7% relative decrease in detection error for fast-flux bot detection, 8.6% for malware traffic detection, 7.3% for malware classification, and 16.9% for face recognition. We explore the limitations and applications of different privileged information techniques in detection systems. Such techniques provide a new means for detection systems to learn from data that would otherwise not be available at runtime.
Tasks	Face Recognition, Malware Classification, Transfer Learning
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09638v4
PDF	http://arxiv.org/pdf/1603.09638v4.pdf
PWC	https://paperswithcode.com/paper/detection-under-privileged-information
Repo
Framework

A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments


Title	A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
Authors	Omer Levy, Anders Søgaard, Yoav Goldberg
Abstract	While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to state-of-the-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.
Tasks	Word Embeddings
Published	2016-08-18
URL	http://arxiv.org/abs/1608.05426v2
PDF	http://arxiv.org/pdf/1608.05426v2.pdf
PWC	https://paperswithcode.com/paper/a-strong-baseline-for-learning-cross-lingual
Repo
Framework

Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network


Title	Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network
Authors	Yu Liu, Jianlong Fu, Tao Mei, Chang Wen Chen
Abstract	Visual storytelling aims to generate human-level narrative language (i.e., a natural paragraph with multiple sentences) from a photo streams. A typical photo story consists of a global timeline with multi-thread local storylines, where each storyline occurs in one different scene. Such complex structure leads to large content gaps at scene transitions between consecutive photos. Most existing image/video captioning methods can only achieve limited performance, because the units in traditional recurrent neural networks (RNN) tend to “forget” the previous state when the visual sequence is inconsistent. In this paper, we propose a novel visual storytelling approach with Bidirectional Multi-thread Recurrent Neural Network (BMRNN). First, based on the mined local storylines, a skip gated recurrent unit (sGRU) with delay control is proposed to maintain longer range visual information. Second, by using sGRU as basic units, the BMRNN is trained to align the local storylines into the global sequential timeline. Third, a new training scheme with a storyline-constrained objective function is proposed by jointly considering both global and local matches. Experiments on three standard storytelling datasets show that the BMRNN model outperforms the state-of-the-art methods.
Tasks	Video Captioning, Visual Storytelling
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00625v1
PDF	http://arxiv.org/pdf/1606.00625v1.pdf
PWC	https://paperswithcode.com/paper/storytelling-of-photo-stream-with
Repo
Framework

Skin Cancer Detection and Tracking using Data Synthesis and Deep Learning


Title	Skin Cancer Detection and Tracking using Data Synthesis and Deep Learning
Authors	Yunzhu Li, Andre Esteva, Brett Kuprel, Rob Novoa, Justin Ko, Sebastian Thrun
Abstract	Dense object detection and temporal tracking are needed across applications domains ranging from people-tracking to analysis of satellite imagery over time. The detection and tracking of malignant skin cancers and benign moles poses a particularly challenging problem due to the general uniformity of large skin patches, the fact that skin lesions vary little in their appearance, and the relatively small amount of data available. Here we introduce a novel data synthesis technique that merges images of individual skin lesions with full-body images and heavily augments them to generate significant amounts of data. We build a convolutional neural network (CNN) based system, trained on this synthetic data, and demonstrate superior performance to traditional detection and tracking techniques. Additionally, we compare our system to humans trained with simple criteria. Our system is intended for potential clinical use to augment the capabilities of healthcare providers. While domain-specific, we believe the methods invoked in this work will be useful in applying CNNs across domains that suffer from limited data availability.
Tasks	Dense Object Detection, Object Detection
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01074v1
PDF	http://arxiv.org/pdf/1612.01074v1.pdf
PWC	https://paperswithcode.com/paper/skin-cancer-detection-and-tracking-using-data
Repo
Framework

Multi-Camera Occlusion and Sudden-Appearance-Change Detection Using Hidden Markovian Chains


Title	Multi-Camera Occlusion and Sudden-Appearance-Change Detection Using Hidden Markovian Chains
Authors	Xudong Ma
Abstract	This paper was originally submitted to Xinova as a response to a Request for Invention (RFI) on new event monitoring methods. In this paper, a new object tracking algorithm using multiple cameras for surveillance applications is proposed. The proposed system can detect sudden-appearance-changes and occlusions using a hidden Markovian statistical model. The experimental results confirm that our system detect the sudden-appearance changes and occlusions reliably.
Tasks	Object Tracking
Published	2016-10-29
URL	http://arxiv.org/abs/1610.09520v1
PDF	http://arxiv.org/pdf/1610.09520v1.pdf
PWC	https://paperswithcode.com/paper/multi-camera-occlusion-and-sudden-appearance
Repo
Framework

Scalable low dimensional manifold model in the reconstruction of noisy and incomplete hyperspectral images


Title	Scalable low dimensional manifold model in the reconstruction of noisy and incomplete hyperspectral images
Authors	Wei Zhu, Zuoqiang Shi, Stanley Osher
Abstract	We present a scalable low dimensional manifold model for the reconstruction of noisy and incomplete hyperspectral images. The model is based on the observation that the spatial-spectral blocks of a hyperspectral image typically lie close to a collection of low dimensional manifolds. To emphasize this, the dimension of the manifold is directly used as a regularizer in a variational functional, which is solved efficiently by alternating direction of minimization and weighted nonlocal Laplacian. Unlike general 3D images, the same similarity matrix can be shared across all spectral bands for a hyperspectral image, therefore the resulting algorithm is much more scalable than that for general 3D data. Numerical experiments on the reconstruction of hyperspectral images from sparse and noisy sampling demonstrate the superiority of our proposed algorithm in terms of both speed and accuracy.
Tasks
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05652v2
PDF	http://arxiv.org/pdf/1605.05652v2.pdf
PWC	https://paperswithcode.com/paper/scalable-low-dimensional-manifold-model-in
Repo
Framework