Paper Group ANR 608
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection. A New Approach for Measuring Sentiment Orientation based on Multi-Dimensional Vector Space. Modeling the Ellsberg Paradox by Argument Strength. Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features. Evasion Attacks against Mach …
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
| Title | Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection |
| Authors | Lina Wei, Fangfang Wang, Xi Li, Fei Wu, Jun Xiao |
| Abstract | As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions. Motivated by this observation, we propose a graph-theoretic video saliency detection approach based on adaptive video structure discovery, which is carried out within a spatiotemporal atomic graph. Through graph-based manifold propagation, the proposed approach is capable of effectively modeling the semantically contextual interactions among atomic video structures for saliency detection while preserving spatial smoothness and temporal consistency. Experiments demonstrate the effectiveness of the proposed approach over several benchmark datasets. |
| Tasks | Saliency Detection, Video Saliency Detection |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07815v1 |
| http://arxiv.org/pdf/1707.07815v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-theoretic-spatiotemporal-context |
| Repo | |
| Framework | |
A New Approach for Measuring Sentiment Orientation based on Multi-Dimensional Vector Space
| Title | A New Approach for Measuring Sentiment Orientation based on Multi-Dimensional Vector Space |
| Authors | Youngsam Kim, Hyopil Shin |
| Abstract | This study implements a vector space model approach to measure the sentiment orientations of words. Two representative vectors for positive/negative polarity are constructed using high-dimensional vec-tor space in both an unsupervised and a semi-supervised manner. A sentiment ori-entation value per word is determined by taking the difference between the cosine distances against the two reference vec-tors. These two conditions (unsupervised and semi-supervised) are compared against an existing unsupervised method (Turney, 2002). As a result of our experi-ment, we demonstrate that this novel ap-proach significantly outperforms the pre-vious unsupervised approach and is more practical and data efficient as well. |
| Tasks | |
| Published | 2017-12-31 |
| URL | http://arxiv.org/abs/1801.00254v1 |
| http://arxiv.org/pdf/1801.00254v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-approach-for-measuring-sentiment |
| Repo | |
| Framework | |
Modeling the Ellsberg Paradox by Argument Strength
| Title | Modeling the Ellsberg Paradox by Argument Strength |
| Authors | Niki Pfeifer, Hanna Pankka |
| Abstract | We present a formal measure of argument strength, which combines the ideas that conclusions of strong arguments are (i) highly probable and (ii) their uncertainty is relatively precise. Likewise, arguments are weak when their conclusion probability is low or when it is highly imprecise. We show how the proposed measure provides a new model of the Ellsberg paradox. Moreover, we further substantiate the psychological plausibility of our approach by an experiment (N = 60). The data show that the proposed measure predicts human inferences in the original Ellsberg task and in corresponding argument strength tasks. Finally, we report qualitative data taken from structured interviews on folk psychological conceptions on what argument strength means. |
| Tasks | |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03233v1 |
| http://arxiv.org/pdf/1703.03233v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-the-ellsberg-paradox-by-argument |
| Repo | |
| Framework | |
Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features
| Title | Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features |
| Authors | Liang Tong, Bo Li, Chen Hajaj, Chaowei Xiao, Ning Zhang, Yevgeniy Vorobeychik |
| Abstract | Machine learning (ML) techniques are increasingly common in security applications, such as malware and intrusion detection. However, ML models are often susceptible to evasion attacks, in which an adversary makes changes to the input (such as malware) in order to avoid being detected. A conventional approach to evaluate ML robustness to such attacks, as well as to design robust ML, is by considering simplified feature-space models of attacks, where the attacker changes ML features directly to effect evasion, while minimizing or constraining the magnitude of this change. We investigate the effectiveness of this approach to designing robust ML in the face of attacks that can be realized in actual malware (realizable attacks). We demonstrate that in the context of structure-based PDF malware detection, such techniques appear to have limited effectiveness, but they are effective with content-based detectors. In either case, we show that augmenting the feature space models with conserved features (those that cannot be unilaterally modified without compromising malicious functionality) significantly improves performance. Finally, we show that feature space models enable generalized robustness when faced with a variety of realizable attacks, as compared to classifiers which are tuned to be robust to a specific realizable attack. |
| Tasks | Intrusion Detection, Malware Detection |
| Published | 2017-08-28 |
| URL | https://arxiv.org/abs/1708.08327v5 |
| https://arxiv.org/pdf/1708.08327v5.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-validating-models-of-evasion |
| Repo | |
| Framework | |
Evasion Attacks against Machine Learning at Test Time
| Title | Evasion Attacks against Machine Learning at Test Time |
| Authors | Battista Biggio, Igino Corona, Davide Maiorca, Blaine Nelson, Nedim Srndic, Pavel Laskov, Giorgio Giacinto, Fabio Roli |
| Abstract | In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system at test time by carefully manipulating attack samples. In this work, we present a simple but effective gradient-based approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks. Following a recently proposed framework for security evaluation, we simulate attack scenarios that exhibit different risk levels for the classifier by increasing the attacker’s knowledge of the system and her ability to manipulate attack samples. This gives the classifier designer a better picture of the classifier performance under evasion attacks, and allows him to perform a more informed model selection (or parameter setting). We evaluate our approach on the relevant security task of malware detection in PDF files, and show that such systems can be easily evaded. We also sketch some countermeasures suggested by our analysis. |
| Tasks | Malware Detection, Model Selection |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06131v1 |
| http://arxiv.org/pdf/1708.06131v1.pdf | |
| PWC | https://paperswithcode.com/paper/evasion-attacks-against-machine-learning-at |
| Repo | |
| Framework | |
Context-aware, Adaptive and Scalable Android Malware Detection through Online Learning (extended version)
| Title | Context-aware, Adaptive and Scalable Android Malware Detection through Online Learning (extended version) |
| Authors | Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu |
| Abstract | It is well-known that Android malware constantly evolves so as to evade detection. This causes the entire malware population to be non-stationary. Contrary to this fact, most of the prior works on Machine Learning based Android malware detection have assumed that the distribution of the observed malware characteristics (i.e., features) does not change over time. In this work, we address the problem of malware population drift and propose a novel online learning based framework to detect malware, named CASANDRA (Contextaware, Adaptive and Scalable ANDRoid mAlware detector). In order to perform accurate detection, a novel graph kernel that facilitates capturing apps’ security-sensitive behaviors along with their context information from dependency graphs is proposed. Besides being accurate and scalable, CASANDRA has specific advantages: i) being adaptive to the evolution in malware features over time ii) explaining the significant features that led to an app’s classification as being malicious or benign. In a large-scale comparative analysis, CASANDRA outperforms two state-of-the-art techniques on a benchmark dataset achieving 99.23% F-measure. When evaluated with more than 87,000 apps collected in-the-wild, CASANDRA achieves 89.92% accuracy, outperforming existing techniques by more than 25% in their typical batch learning setting and more than 7% when they are continuously retained, while maintaining comparable efficiency. |
| Tasks | Android Malware Detection, Malware Detection |
| Published | 2017-06-03 |
| URL | http://arxiv.org/abs/1706.00947v2 |
| http://arxiv.org/pdf/1706.00947v2.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-adaptive-and-scalable-android |
| Repo | |
| Framework | |
Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition
| Title | Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition |
| Authors | Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon |
| Abstract | Recent advances in visual recognition show overarching success by virtue of large amounts of supervised data. However,the acquisition of a large supervised dataset is often challenging. This is also true for intelligent transportation applications, i.e., traffic sign recognition. For example, a model trained with data of one country may not be easily generalized to another country without much data. We propose a novel feature embedding scheme for unseen class classification when the representative class template is given. Traffic signs, unlike other objects, have official images. We perform co-domain embedding using a quadruple relationship from real and synthetic domains. Our quadruplet network fully utilizes the explicit pairwise similarity relationships among samples from different domains. We validate our method on three datasets with two experiments involving one-shot classification and feature generalization. The results show that the proposed method outperforms competing approaches on both seen and unseen classes. |
| Tasks | Traffic Sign Recognition |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01907v1 |
| http://arxiv.org/pdf/1712.01907v1.pdf | |
| PWC | https://paperswithcode.com/paper/co-domain-embedding-using-deep-quadruplet |
| Repo | |
| Framework | |
A Nonlinear Dimensionality Reduction Framework Using Smooth Geodesics
| Title | A Nonlinear Dimensionality Reduction Framework Using Smooth Geodesics |
| Authors | Kelum Gajamannage, Randy Paffenroth, Erik M. Bollt |
| Abstract | Existing dimensionality reduction methods are adept at revealing hidden underlying manifolds arising from high-dimensional data and thereby producing a low-dimensional representation. However, the smoothness of the manifolds produced by classic techniques over sparse and noisy data is not guaranteed. In fact, the embedding generated using such data may distort the geometry of the manifold and thereby produce an unfaithful embedding. Herein, we propose a framework for nonlinear dimensionality reduction that generates a manifold in terms of smooth geodesics that is designed to treat problems in which manifold measurements are either sparse or corrupted by noise. Our method generates a network structure for given high-dimensional data using a nearest neighbors search and then produces piecewise linear shortest paths that are defined as geodesics. Then, we fit points in each geodesic by a smoothing spline to emphasize the smoothness. The robustness of this approach for sparse and noisy datasets is demonstrated by the implementation of the method on synthetic and real-world datasets. |
| Tasks | Dimensionality Reduction |
| Published | 2017-07-21 |
| URL | http://arxiv.org/abs/1707.06757v2 |
| http://arxiv.org/pdf/1707.06757v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-nonlinear-dimensionality-reduction |
| Repo | |
| Framework | |
An Extensive Technique to Detect and Analyze Melanoma: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2017
| Title | An Extensive Technique to Detect and Analyze Melanoma: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2017 |
| Authors | G Wiselin Jiji, P Johnson Durai Raj |
| Abstract | An automated method to detect and analyze the melanoma is presented to improve diagnosis which will leads to the exact treatment. Image processing techniques such as segmentation, feature descriptors and classification models are involved in this method. In the First phase the lesion region is segmented using CIELAB Color space Based Segmentation. Then feature descriptors such as shape, color and texture are extracted. Finally, in the third phase lesion region is classified as melanoma, seborrheic keratosis or nevus using multi class O-A SVM model. Experiment with ISIC 2017 Archive skin image database has been done and analyzed the results. |
| Tasks | |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08717v1 |
| http://arxiv.org/pdf/1702.08717v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-extensive-technique-to-detect-and-analyze |
| Repo | |
| Framework | |
Joint auto-encoders: a flexible multi-task learning framework
| Title | Joint auto-encoders: a flexible multi-task learning framework |
| Authors | Baruch Epstein. Ron Meir, Tomer Michaeli |
| Abstract | The incorporation of prior knowledge into learning is essential in achieving good performance based on small noisy samples. Such knowledge is often incorporated through the availability of related data arising from domains and tasks similar to the one of current interest. Ideally one would like to allow both the data for the current task and for previous related tasks to self-organize the learning system in such a way that commonalities and differences between the tasks are learned in a data-driven fashion. We develop a framework for learning multiple tasks simultaneously, based on sharing features that are common to all tasks, achieved through the use of a modular deep feedforward neural network consisting of shared branches, dealing with the common features of all tasks, and private branches, learning the specific unique aspects of each task. Once an appropriate weight sharing architecture has been established, learning takes place through standard algorithms for feedforward networks, e.g., stochastic gradient descent and its variations. The method deals with domain adaptation and multi-task learning in a unified fashion, and can easily deal with data arising from different types of sources. Numerical experiments demonstrate the effectiveness of learning in domain adaptation and transfer learning setups, and provide evidence for the flexible and task-oriented representations arising in the network. |
| Tasks | Domain Adaptation, Multi-Task Learning, Transfer Learning |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10494v1 |
| http://arxiv.org/pdf/1705.10494v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-auto-encoders-a-flexible-multi-task |
| Repo | |
| Framework | |
Persian Wordnet Construction using Supervised Learning
| Title | Persian Wordnet Construction using Supervised Learning |
| Authors | Zahra Mousavi, Heshaam Faili |
| Abstract | This paper presents an automated supervised method for Persian wordnet construction. Using a Persian corpus and a bi-lingual dictionary, the initial links between Persian words and Princeton WordNet synsets have been generated. These links will be discriminated later as correct or incorrect by employing seven features in a trained classification system. The whole method is just a classification system, which has been trained on a train set containing FarsNet as a set of correct instances. State of the art results on the automatically derived Persian wordnet is achieved. The resulted wordnet with a precision of 91.18% includes more than 16,000 words and 22,000 synsets. |
| Tasks | |
| Published | 2017-04-11 |
| URL | http://arxiv.org/abs/1704.03223v1 |
| http://arxiv.org/pdf/1704.03223v1.pdf | |
| PWC | https://paperswithcode.com/paper/persian-wordnet-construction-using-supervised |
| Repo | |
| Framework | |
EMULATOR vs REAL PHONE: Android Malware Detection Using Machine Learning
| Title | EMULATOR vs REAL PHONE: Android Malware Detection Using Machine Learning |
| Authors | Mohammed K. Alzaylaee, Suleiman Y. Yerima, Sakir Sezer |
| Abstract | The Android operating system has become the most popular operating system for smartphones and tablets leading to a rapid rise in malware. Sophisticated Android malware employ detection avoidance techniques in order to hide their malicious activities from analysis tools. These include a wide range of anti-emulator techniques, where the malware programs attempt to hide their malicious activities by detecting the emulator. For this reason, countermeasures against antiemulation are becoming increasingly important in Android malware detection. Analysis and detection based on real devices can alleviate the problems of anti-emulation as well as improve the effectiveness of dynamic analysis. Hence, in this paper we present an investigation of machine learning based malware detection using dynamic analysis on real devices. A tool is implemented to automatically extract dynamic features from Android phones and through several experiments, a comparative analysis of emulator based vs. device based detection by means of several machine learning algorithms is undertaken. Our study shows that several features could be extracted more effectively from the on-device dynamic analysis compared to emulators. It was also found that approximately 24% more apps were successfully analysed on the phone. Furthermore, all of the studied machine learning based detection performed better when applied to features extracted from the on-device dynamic analysis. |
| Tasks | Android Malware Detection, Malware Detection |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1703.10926v1 |
| http://arxiv.org/pdf/1703.10926v1.pdf | |
| PWC | https://paperswithcode.com/paper/emulator-vs-real-phone-android-malware |
| Repo | |
| Framework | |
QuickNet: Maximizing Efficiency and Efficacy in Deep Architectures
| Title | QuickNet: Maximizing Efficiency and Efficacy in Deep Architectures |
| Authors | Tapabrata Ghosh |
| Abstract | We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it more memory efficient. We do this by making two major modifications to the reference Darknet model (Redmon et al, 2015): 1) The use of depthwise separable convolutions and 2) The use of parametric rectified linear units. We make the observation that parametric rectified linear units are computationally equivalent to leaky rectified linear units at test time and the observation that separable convolutions can be interpreted as a compressed Inception network (Chollet, 2016). Using these observations, we derive a network architecture, which we call QuickNet, that is both faster and more accurate than previous models. Our architecture provides at least four major advantages: (1) A smaller model size, which is more tenable on memory constrained systems; (2) A significantly faster network which is more tenable on computationally constrained systems; (3) A high accuracy of 95.7 percent on the CIFAR-10 Dataset which outperforms all but one result published so far, although we note that our works are orthogonal approaches and can be combined (4) Orthogonality to previous model compression approaches allowing for further speed gains to be realized. |
| Tasks | Model Compression |
| Published | 2017-01-09 |
| URL | http://arxiv.org/abs/1701.02291v2 |
| http://arxiv.org/pdf/1701.02291v2.pdf | |
| PWC | https://paperswithcode.com/paper/quicknet-maximizing-efficiency-and-efficacy |
| Repo | |
| Framework | |
Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking
| Title | Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking |
| Authors | Erwin Quiring, Daniel Arp, Konrad Rieck |
| Abstract | Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are vulnerable to different types of attacks. This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods. Concurrently, a different line of research has tackled a very similar problem: In digital watermarking information are embedded in a signal in the presence of an adversary. As a consequence, this research field has also extensively studied techniques for attacking and defending watermarking methods. The two research communities have worked in parallel so far, unnoticeably developing similar attack and defense strategies. This paper is a first effort to bring these communities together. To this end, we present a unified notation of black-box attacks against machine learning and watermarking that reveals the similarity of both settings. To demonstrate the efficacy of this unified view, we apply concepts from watermarking to machine learning and vice versa. We show that countermeasures from watermarking can mitigate recent model-extraction attacks and, similarly, that techniques for hardening machine learning can fend off oracle attacks against watermarks. Our work provides a conceptual link between two research fields and thereby opens novel directions for improving the security of both, machine learning and digital watermarking. |
| Tasks | Autonomous Driving, Face Recognition, Malware Detection |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05561v1 |
| http://arxiv.org/pdf/1703.05561v1.pdf | |
| PWC | https://paperswithcode.com/paper/fraternal-twins-unifying-attacks-on-machine |
| Repo | |
| Framework | |
DeepNav: Learning to Navigate Large Cities
| Title | DeepNav: Learning to Navigate Large Cities |
| Authors | Samarth Brahmbhatt, James Hays |
| Abstract | We present DeepNav, a Convolutional Neural Network (CNN) based algorithm for navigating large cities using locally visible street-view images. The DeepNav agent learns to reach its destination quickly by making the correct navigation decisions at intersections. We collect a large-scale dataset of street-view images organized in a graph where nodes are connected by roads. This dataset contains 10 city graphs and more than 1 million street-view images. We propose 3 supervised learning approaches for the navigation task and show how A* search in the city graph can be used to generate supervision for the learning. Our annotation process is fully automated using publicly available mapping services and requires no human input. We evaluate the proposed DeepNav models on 4 held-out cities for navigating to 5 different types of destinations. Our algorithms outperform previous work that uses hand-crafted features and Support Vector Regression (SVR)[19]. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.09135v2 |
| http://arxiv.org/pdf/1701.09135v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepnav-learning-to-navigate-large-cities |
| Repo | |
| Framework | |
