Paper Group ANR 328
Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection. Digital Watermarking for Deep Neural Networks. An investigation of a deep learning based malware detection system. Solving Weakly-Convex-Weakly-Concave Saddle-Point Problems as Successive Strongly Monotone Variational Inequalities. Static Malware Det …
Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection
| Title | Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection |
| Authors | Mohit Sewak, Sanjay K. Sahay, Hemant Rathore |
| Abstract | Recently, Deep Learning has been showing promising results in various Artificial Intelligence applications like image recognition, natural language processing, language modeling, neural machine translation, etc. Although, in general, it is computationally more expensive as compared to classical machine learning techniques, their results are found to be more effective in some cases. Therefore, in this paper, we investigated and compared one of the Deep Learning Architecture called Deep Neural Network (DNN) with the classical Random Forest (RF) machine learning algorithm for the malware classification. We studied the performance of the classical RF and DNN with 2, 4 & 7 layers architectures with the four different feature sets, and found that irrespective of the features inputs, the classical RF accuracy outperforms the DNN. |
| Tasks | Language Modelling, Machine Translation, Malware Classification, Malware Detection |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05889v1 |
| http://arxiv.org/pdf/1809.05889v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-deep-learning-and-the-classical |
| Repo | |
| Framework | |
Digital Watermarking for Deep Neural Networks
| Title | Digital Watermarking for Deep Neural Networks |
| Authors | Yuki Nagai, Yusuke Uchida, Shigeyuki Sakazawa, Shin’ichi Satoh |
| Abstract | Although deep neural networks have made tremendous progress in the area of multimedia representation, training neural models requires a large amount of data and time. It is well-known that utilizing trained models as initial weights often achieves lower training error than neural networks that are not pre-trained. A fine-tuning step helps to reduce both the computational cost and improve performance. Therefore, sharing trained models has been very important for the rapid progress of research and development. In addition, trained models could be important assets for the owner(s) who trained them, hence we regard trained models as intellectual property. In this paper, we propose a digital watermarking technology for ownership authorization of deep neural networks. First, we formulate a new problem: embedding watermarks into deep neural networks. We also define requirements, embedding situations, and attack types on watermarking in deep neural networks. Second, we propose a general framework for embedding a watermark in model parameters, using a parameter regularizer. Our approach does not impair the performance of networks into which a watermark is placed because the watermark is embedded while training the host network. Finally, we perform comprehensive experiments to reveal the potential of watermarking deep neural networks as the basis of this new research effort. We show that our framework can embed a watermark during the training of a deep neural network from scratch, and during fine-tuning and distilling, without impairing its performance. The embedded watermark does not disappear even after fine-tuning or parameter pruning; the watermark remains complete even after 65% of parameters are pruned. |
| Tasks | |
| Published | 2018-02-06 |
| URL | http://arxiv.org/abs/1802.02601v1 |
| http://arxiv.org/pdf/1802.02601v1.pdf | |
| PWC | https://paperswithcode.com/paper/digital-watermarking-for-deep-neural-networks |
| Repo | |
| Framework | |
An investigation of a deep learning based malware detection system
| Title | An investigation of a deep learning based malware detection system |
| Authors | Mohit Sewak, Sanjay K. Sahay, Hemant Rathore |
| Abstract | We investigate a Deep Learning based system for malware detection. In the investigation, we experiment with different combination of Deep Learning architectures including Auto-Encoders, and Deep Neural Networks with varying layers over Malicia malware dataset on which earlier studies have obtained an accuracy of (98%) with an acceptable False Positive Rates (1.07%). But these results were done using extensive man-made custom domain features and investing corresponding feature engineering and design efforts. In our proposed approach, besides improving the previous best results (99.21% accuracy and a False Positive Rate of 0.19%) indicates that Deep Learning based systems could deliver an effective defense against malware. Since it is good in automatically extracting higher conceptual features from the data, Deep Learning based systems could provide an effective, general and scalable mechanism for detection of existing and unknown malware. |
| Tasks | Feature Engineering, Malware Detection |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05888v1 |
| http://arxiv.org/pdf/1809.05888v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-investigation-of-a-deep-learning-based |
| Repo | |
| Framework | |
Solving Weakly-Convex-Weakly-Concave Saddle-Point Problems as Successive Strongly Monotone Variational Inequalities
| Title | Solving Weakly-Convex-Weakly-Concave Saddle-Point Problems as Successive Strongly Monotone Variational Inequalities |
| Authors | Qihang Lin, Mingrui Liu, Hassan Rafique, Tianbao Yang |
| Abstract | In this paper, we consider first-order algorithms for solving a class of non-convex non-concave min-max saddle-point problems, whose objective function is weakly convex (resp. weakly concave) in terms of the variable of minimization (resp. maximization). It has many important applications in machine learning, statistics, and operations research. One such example that attracts tremendous attention recently in machine learning is training Generative Adversarial Networks. We propose an algorithmic framework motivated by the inexact proximal point method, which solves the weakly monotone variational inequality corresponding to the original min-max problem by approximately solving a sequence of strongly monotone variational inequalities constructed by adding a strongly monotone mapping to the original gradient mapping. In this sequence, each strongly monotone variational inequality is defined with a proximal center that is updated using the approximate solution of the previous variational inequality. Our algorithm generates a sequence of solution that provably converges to a nearly stationary solution of the original min-max problem. The proposed framework is flexible because various subroutines can be employed for solving the strongly monotone variational inequalities. The overall computational complexities of our methods are established when the employed subroutines are subgradient method, stochastic subgradient method, gradient descent method and Nesterov’s accelerated method and variance reduction methods for a Lipschitz continuous operator. To the best of our knowledge, this is the first work that establishes the non-asymptotic convergence to a nearly stationary point of a non-convex non-concave min-max problem. |
| Tasks | |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10207v2 |
| http://arxiv.org/pdf/1810.10207v2.pdf | |
| PWC | https://paperswithcode.com/paper/solving-weakly-convex-weakly-concave-saddle |
| Repo | |
| Framework | |
Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus
| Title | Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus |
| Authors | William Fleshman, Edward Raff, Richard Zak, Mark McLean, Charles Nicholas |
| Abstract | As machine-learning (ML) based systems for malware detection become more prevalent, it becomes necessary to quantify the benefits compared to the more traditional anti-virus (AV) systems widely used today. It is not practical to build an agreed upon test set to benchmark malware detection systems on pure classification performance. Instead we tackle the problem by creating a new testing methodology, where we evaluate the change in performance on a set of known benign & malicious files as adversarial modifications are performed. The change in performance combined with the evasion techniques then quantifies a system’s robustness against that approach. Through these experiments we are able to show in a quantifiable way how purely ML based systems can be more robust than AV products at detecting malware that attempts evasion through modification, but may be slower to adapt in the face of significantly novel attacks. |
| Tasks | Malware Detection |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04773v1 |
| http://arxiv.org/pdf/1806.04773v1.pdf | |
| PWC | https://paperswithcode.com/paper/static-malware-detection-subterfuge |
| Repo | |
| Framework | |
Optimal Learning with Anisotropic Gaussian SVMs
| Title | Optimal Learning with Anisotropic Gaussian SVMs |
| Authors | Hanyuan Hang, Ingo Steinwart |
| Abstract | This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain anisotropic Besov spaces, we establish the almost optimal learning rates, more precisely, optimal up to some logarithmic factor, presented by the effective smoothness. By taking the effective smoothness into consideration, our almost optimal learning rates are faster than those obtained with the underlying RKHSs being certain anisotropic Sobolev spaces. Moreover, if the target function depends only on fewer dimensions, faster learning rates can be further achieved. |
| Tasks | |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02321v1 |
| http://arxiv.org/pdf/1810.02321v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-learning-with-anisotropic-gaussian |
| Repo | |
| Framework | |
ML + FV = $\heartsuit$? A Survey on the Application of Machine Learning to Formal Verification
| Title | ML + FV = $\heartsuit$? A Survey on the Application of Machine Learning to Formal Verification |
| Authors | Moussa Amrani, Levi Lúcio, Adrien Bibal |
| Abstract | Formal Verification (FV) and Machine Learning (ML) can seem incompatible due to their opposite mathematical foundations and their use in real-life problems: FV mostly relies on discrete mathematics and aims at ensuring correctness; ML often relies on probabilistic models and consists of learning patterns from training data. In this paper, we postulate that they are complementary in practice, and explore how ML helps FV in its classical approaches: static analysis, model-checking, theorem-proving, and SAT solving. We draw a landscape of the current practice and catalog some of the most prominent uses of ML inside FV tools, thus offering a new perspective on FV techniques that can help researchers and practitioners to better locate the possible synergies. We discuss lessons learned from our work, point to possible improvements and offer visions for the future of the domain in the light of the science of software and systems modeling. |
| Tasks | Automated Theorem Proving |
| Published | 2018-06-10 |
| URL | http://arxiv.org/abs/1806.03600v2 |
| http://arxiv.org/pdf/1806.03600v2.pdf | |
| PWC | https://paperswithcode.com/paper/ml-fv-heartsuit-a-survey-on-the-application |
| Repo | |
| Framework | |
Can We Use Speaker Recognition Technology to Attack Itself? Enhancing Mimicry Attacks Using Automatic Target Speaker Selection
| Title | Can We Use Speaker Recognition Technology to Attack Itself? Enhancing Mimicry Attacks Using Automatic Target Speaker Selection |
| Authors | Tomi Kinnunen, Rosa González Hautamäki, Ville Vestman, Md Sahidullah |
| Abstract | We consider technology-assisted mimicry attacks in the context of automatic speaker verification (ASV). We use ASV itself to select targeted speakers to be attacked by human-based mimicry. We recorded 6 naive mimics for whom we select target celebrities from VoxCeleb1 and VoxCeleb2 corpora (7,365 potential targets) using an i-vector system. The attacker attempts to mimic the selected target, with the utterances subjected to ASV tests using an independently developed x-vector system. Our main finding is negative: even if some of the attacker scores against the target speakers were slightly increased, our mimics did not succeed in spoofing the x-vector system. Interestingly, however, the relative ordering of the selected targets (closest, furthest, median) are consistent between the systems, which suggests some level of transferability between the systems. |
| Tasks | Speaker Recognition, Speaker Verification |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.03790v1 |
| http://arxiv.org/pdf/1811.03790v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-we-use-speaker-recognition-technology-to |
| Repo | |
| Framework | |
3D Fluid Flow Estimation with Integrated Particle Reconstruction
| Title | 3D Fluid Flow Estimation with Integrated Particle Reconstruction |
| Authors | Katrin Lasinger, Christoph Vogel, Thomas Pock, Konrad Schindler |
| Abstract | The standard approach to densely reconstruct the motion in a volume of fluid is to inject high-contrast tracer particles and record their motion with multiple high-speed cameras. Almost all existing work processes the acquired multi-view video in two separate steps, utilizing either a pure Eulerian or pure Lagrangian approach. Eulerian methods perform a voxel-based reconstruction of particles per time step, followed by 3D motion estimation, with some form of dense matching between the precomputed voxel grids from different time steps. In this sequential procedure, the first step cannot use temporal consistency considerations to support the reconstruction, while the second step has no access to the original, high-resolution image data. Alternatively, Lagrangian methods reconstruct an explicit, sparse set of particles and track the individual particles over time. Physical constraints can only be incorporated in a post-processing step when interpolating the particle tracks to a dense motion field. We show, for the first time, how to jointly reconstruct both the individual tracer particles and a dense 3D fluid motion field from the image data, using an integrated energy minimization. Our hybrid Lagrangian/Eulerian model reconstructs individual particles, and at the same time recovers a dense 3D motion field in the entire domain. Making particles explicit greatly reduces the memory consumption and allows one to use the high-res input images for matching. Whereas the dense motion field makes it possible to include physical a-priori constraints and account for the incompressibility and viscosity of the fluid. The method exhibits greatly (~70%) improved results over our recently published baseline with two separate steps for 3D reconstruction and motion estimation. Our results with only two time steps are comparable to those of sota tracking-based methods that require much longer sequences. |
| Tasks | 3D Reconstruction, Motion Estimation |
| Published | 2018-04-09 |
| URL | https://arxiv.org/abs/1804.03037v3 |
| https://arxiv.org/pdf/1804.03037v3.pdf | |
| PWC | https://paperswithcode.com/paper/3d-fluid-flow-estimation-with-integrated |
| Repo | |
| Framework | |
Coordinated Heterogeneous Distributed Perception based on Latent Space Representation
| Title | Coordinated Heterogeneous Distributed Perception based on Latent Space Representation |
| Authors | Timo Korthals, Jürgen Leitner, Ulrich Rückert |
| Abstract | We investigate a reinforcement approach for distributed sensing based on the latent space derived from multi-modal deep generative models. Our contribution provides insights to the following benefits: Detections can be exchanged effectively between robots equipped with uni-modal sensors due to a shared latent representation of information that is trained by a Variational Auto Encoder (VAE). Sensor-fusion can be applied asynchronously due to the generative feature of the VAE. Deep Q-Networks (DQNs) are trained to minimize uncertainty in latent space by coordinating robots to a Point-of-Interest (PoI) where their sensor modality can provide beneficial information about the PoI. Additionally, we show that the decrease in uncertainty can be defined as the direct reward signal for training the DQN. |
| Tasks | Sensor Fusion |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04558v1 |
| http://arxiv.org/pdf/1809.04558v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordinated-heterogeneous-distributed |
| Repo | |
| Framework | |
ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators
| Title | ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators |
| Authors | Jeff Zhang, Kartheek Rangineni, Zahra Ghodsi, Siddharth Garg |
| Abstract | Hardware accelerators are being increasingly deployed to boost the performance and energy efficiency of deep neural network (DNN) inference. In this paper we propose Thundervolt, a new framework that enables aggressive voltage underscaling of high-performance DNN accelerators without compromising classification accuracy even in the presence of high timing error rates. Using post-synthesis timing simulations of a DNN accelerator modeled on the Google TPU, we show that Thundervolt enables between 34%-57% energy savings on state-of-the-art speech and image recognition benchmarks with less than 1% loss in classification accuracy and no performance loss. Further, we show that Thundervolt is synergistic with and can further increase the energy efficiency of commonly used run-time DNN pruning techniques like Zero-Skip. |
| Tasks | |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03806v2 |
| http://arxiv.org/pdf/1802.03806v2.pdf | |
| PWC | https://paperswithcode.com/paper/thundervolt-enabling-aggressive-voltage |
| Repo | |
| Framework | |
LRS3-TED: a large-scale dataset for visual speech recognition
| Title | LRS3-TED: a large-scale dataset for visual speech recognition |
| Authors | Triantafyllos Afouras, Joon Son Chung, Andrew Zisserman |
| Abstract | This paper introduces a new multi-modal dataset for visual and audio-visual speech recognition. It includes face tracks from over 400 hours of TED and TEDx videos, along with the corresponding subtitles and word alignment boundaries. The new dataset is substantially larger in scale compared to other public datasets that are available for general research. |
| Tasks | Audio-Visual Speech Recognition, Speech Recognition, Visual Speech Recognition, Word Alignment |
| Published | 2018-09-03 |
| URL | http://arxiv.org/abs/1809.00496v2 |
| http://arxiv.org/pdf/1809.00496v2.pdf | |
| PWC | https://paperswithcode.com/paper/lrs3-ted-a-large-scale-dataset-for-visual |
| Repo | |
| Framework | |
Semantic segmentation of mFISH images using convolutional networks
| Title | Semantic segmentation of mFISH images using convolutional networks |
| Authors | Esteban Pardo, José Mário T Morgado, Norberto Malpica |
| Abstract | Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current methods of image analysis. |
| Tasks | Semantic Segmentation |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01220v1 |
| http://arxiv.org/pdf/1805.01220v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-segmentation-of-mfish-images-using |
| Repo | |
| Framework | |
Fast Piecewise-Affine Motion Estimation Without Segmentation
| Title | Fast Piecewise-Affine Motion Estimation Without Segmentation |
| Authors | Denis Fortun, Martin Storath, Dennis Rickert, Andreas Weinmann, Michael Unser |
| Abstract | Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this end, we reformulate the problem by imposing piecewise constancy of the parameter field, and derive a specific proximal splitting optimization scheme. A key component of our framework is an efficient one-dimensional piecewise-affine estimator for vector-valued signals. The first advantage of our approach over segmentation-based methods is its absence of initialization. The second advantage is its lower computational cost which is independent of the complexity of the motion field. In addition to these features, we demonstrate competitive accuracy with other piecewise-parametric methods on standard evaluation benchmarks. Our new regularization scheme also outperforms the more standard use of total variation and total generalized variation. |
| Tasks | Motion Estimation, Motion Segmentation |
| Published | 2018-02-06 |
| URL | http://arxiv.org/abs/1802.01872v1 |
| http://arxiv.org/pdf/1802.01872v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-piecewise-affine-motion-estimation |
| Repo | |
| Framework | |
Using Social Network Information in Bayesian Truth Discovery
| Title | Using Social Network Information in Bayesian Truth Discovery |
| Authors | Jielong Yang, Junshan Wang, Wee Peng Tay |
| Abstract | We investigate the problem of truth discovery based on opinions from multiple agents who may be unreliable or biased. We consider the case where agents’ reliabilities or biases are correlated if they belong to the same community, which defines a group of agents with similar opinions regarding a particular event. An agent can belong to different communities for different events, and these communities are unknown a priori. We incorporate knowledge of the agents’ social network in our truth discovery framework and develop Laplace variational inference methods to estimate agents’ reliabilities, communities, and the event states. We also develop a stochastic variational inference method to scale our model to large social networks. Simulations and experiments on real data suggest that when observations are sparse, our proposed methods perform better than several other inference methods, including majority voting, TruthFinder, AccuSim, the Confidence-Aware Truth Discovery method, the Bayesian Classifier Combination (BCC) method, and the Community BCC method. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.02954v3 |
| http://arxiv.org/pdf/1806.02954v3.pdf | |
| PWC | https://paperswithcode.com/paper/using-social-network-information-in-bayesian |
| Repo | |
| Framework | |
