January 26, 2020

3008 words 15 mins read

Paper Group ANR 1350

The iWildCam 2019 Challenge Dataset. The Bias-Expressivity Trade-off. ALOHA: Auxiliary Loss Optimization for Hypothesis Augmentation. Agent-based Vs Agent-less Sandbox for Dynamic Behavioral Analysis. Safe Policy Improvement with an Estimated Baseline Policy. Perception-Distortion Trade-off with Restricted Boltzmann Machines. Adversarial Samples on …

The iWildCam 2019 Challenge Dataset


Title	The iWildCam 2019 Challenge Dataset
Authors	Sara Beery, Dan Morris, Pietro Perona
Abstract	Camera Traps (or Wild Cams) enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor biodiversity and population density of animal species. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but as we try to expand the scope of these models from specific regions where we have collected training data to different areas we are faced with an interesting problem: how do you classify a species in a new region that you may not have seen in previous training data? In order to tackle this problem, we have prepared a dataset and challenge where the training data and test data are from different regions, namely The American Southwest and the American Northwest. We use the Caltech Camera Traps dataset, collected from the American Southwest, as training data. We add a new dataset from the American Northwest, curated from data provided by the Idaho Department of Fish and Game (IDFG), as our test dataset. The test data has some class overlap with the training data, some species are found in both datasets, but there are both species seen during training that are not seen during test and vice versa. To help fill the gaps in the training species, we allow competitors to utilize transfer learning from two alternate domains: human-curated images from iNaturalist and synthetic images from Microsoft’s TrapCam-AirSim simulation environment.
Tasks	Transfer Learning
Published	2019-07-15
URL	https://arxiv.org/abs/1907.07617v1
PDF	https://arxiv.org/pdf/1907.07617v1.pdf
PWC	https://paperswithcode.com/paper/the-iwildcam-2019-challenge-dataset
Repo
Framework

The Bias-Expressivity Trade-off


Title	The Bias-Expressivity Trade-off
Authors	Julius Lauw, Dominique Macias, Akshay Trikha, Julia Vendemiatti, George D. Montanez
Abstract	Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on changes in its input. We measure expressivity by using an information-theoretic notion of entropy on algorithm outcome distributions, demonstrating a trade-off between bias and expressivity. To the degree an algorithm is biased is the degree to which it can outperform uniform random sampling, but is also the degree to which is becomes inflexible. We derive bounds relating bias to expressivity, proving the necessary trade-offs inherent in trying to create strongly performing yet flexible algorithms.
Tasks
Published	2019-11-09
URL	https://arxiv.org/abs/1911.04964v1
PDF	https://arxiv.org/pdf/1911.04964v1.pdf
PWC	https://paperswithcode.com/paper/the-bias-expressivity-trade-off
Repo
Framework

ALOHA: Auxiliary Loss Optimization for Hypothesis Augmentation


Title	ALOHA: Auxiliary Loss Optimization for Hypothesis Augmentation
Authors	Ethan M. Rudd, Felipe N. Ducau, Cody Wild, Konstantin Berlin, Richard Harang
Abstract	Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically optimized such that outputs from the model over a set of input samples most closely match the samples’ true malicious/benign (1/0) target labels. However, there are often a number of other sources of contextual metadata for each malware sample, beyond an aggregate malicious/benign label, including multiple labeling sources and malware type information (e.g., ransomware, trojan, etc.), which we can feed to the classifier as auxiliary prediction targets. In this work, we fit deep neural networks to multiple additional targets derived from metadata in a threat intelligence feed for Portable Executable (PE) malware and benignware, including a multi-source malicious/benign loss, a count loss on multi-source detections, and a semantic malware attribute tag loss. We find that incorporating multiple auxiliary loss terms yields a marked improvement in performance on the main detection task. We also demonstrate that these gains likely stem from a more informed neural network representation and are not due to a regularization artifact of multi-target learning. Our auxiliary loss architecture yields a significant reduction in detection error rate (false negatives) of 42.6% at a false positive rate (FPR) of $10^{-3}$ when compared to a similar model with only one target, and a decrease of 53.8% at $10^{-5}$ FPR.
Tasks	Malware Detection
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05700v1
PDF	http://arxiv.org/pdf/1903.05700v1.pdf
PWC	https://paperswithcode.com/paper/aloha-auxiliary-loss-optimization-for
Repo
Framework

Agent-based Vs Agent-less Sandbox for Dynamic Behavioral Analysis


Title	Agent-based Vs Agent-less Sandbox for Dynamic Behavioral Analysis
Authors	Muhammad Ali, Stavros Shiaeles, Maria Papadaki, Bogdan Ghita
Abstract	Malicious software is detected and classified by either static analysis or dynamic analysis. In static analysis, malware samples are reverse engineered and analyzed so that signatures of malware can be constructed. These techniques can be easily thwarted through polymorphic, metamorphic malware, obfuscation and packing techniques, whereas in dynamic analysis malware samples are executed in a controlled environment using the sandboxing technique, in order to model the behavior of malware. In this paper, we have analyzed Petya, Spyeye, VolatileCedar, PAFISH etc. through Agent-based and Agentless dynamic sandbox systems in order to investigate and benchmark their efficiency in advanced malware detection.
Tasks	Malware Detection
Published	2019-03-12
URL	http://arxiv.org/abs/1904.02100v1
PDF	http://arxiv.org/pdf/1904.02100v1.pdf
PWC	https://paperswithcode.com/paper/agent-based-vs-agent-less-sandbox-for-dynamic
Repo
Framework

Safe Policy Improvement with an Estimated Baseline Policy


Title	Safe Policy Improvement with an Estimated Baseline Policy
Authors	Thiago D. Simão, Romain Laroche, Rémi Tachet des Combes
Abstract	Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on the trained policy performance. However, in many real-world applications such as dialogue systems, pharmaceutical tests or crop management, data is collected under human supervision and the baseline remains unknown. In this paper, we apply SPIBB algorithms with a baseline estimate built from the data. We formally show safe policy improvement guarantees over the true baseline even without direct access to it. Our empirical experiments on finite and continuous states tasks support the theoretical findings. It shows little loss of performance in comparison with SPIBB when the baseline policy is given, and more importantly, drastically and significantly outperforms competing algorithms both in safe policy improvement, and in average performance.
Tasks
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05236v1
PDF	https://arxiv.org/pdf/1909.05236v1.pdf
PWC	https://paperswithcode.com/paper/safe-policy-improvement-with-an-estimated
Repo
Framework

Perception-Distortion Trade-off with Restricted Boltzmann Machines


Title	Perception-Distortion Trade-off with Restricted Boltzmann Machines
Authors	Chris Cannella, Jie Ding, Mohammadreza Soltani, Vahid Tarokh
Abstract	In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations. We compare the performance of our proposed procedure with those obtained using existing reconstruction procedures trained on incomplete data. We place these performance comparisons within the context of the perception-distortion trade-off observed in other data reconstruction tasks, which has, until now, remained unexplored in tasks relying on incomplete training data.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09122v1
PDF	https://arxiv.org/pdf/1910.09122v1.pdf
PWC	https://paperswithcode.com/paper/perception-distortion-trade-off-with
Repo
Framework

Adversarial Samples on Android Malware Detection Systems for IoT Systems


Title	Adversarial Samples on Android Malware Detection Systems for IoT Systems
Authors	Xiaolei Liu, Xiaojiang Du, Xiaosong Zhang, Qingxin Zhu, Mohsen Guizani
Abstract	Many IoT(Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vulnerable to adversarial samples. An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis. The current methods of generating adversarial samples mostly require training parameters of models and most of the methods are aimed at image data. To solve this problem, we propose a \textbf{t}esting framework for \textbf{l}earning-based \textbf{A}ndroid \textbf{m}alware \textbf{d}etection systems(TLAMD) for IoT Devices. The key challenge is how to construct a suitable fitness function to generate an effective adversarial sample without affecting the features of the application. By introducing genetic algorithms and some technical improvements, our test framework can generate adversarial samples for the IoT Android Application with a success rate of nearly 100% and can perform black-box testing on the system.
Tasks	Android Malware Detection, Malware Detection
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04238v1
PDF	http://arxiv.org/pdf/1902.04238v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-samples-on-android-malware
Repo
Framework

Machine Learning With Feature Selection Using Principal Component Analysis for Malware Detection: A Case Study


Title	Machine Learning With Feature Selection Using Principal Component Analysis for Malware Detection: A Case Study
Authors	Jason Zhang
Abstract	Cyber security threats have been growing significantly in both volume and sophistication over the past decade. This poses great challenges to malware detection without considerable automation. In this paper, we have proposed a novel approach by extending our recently suggested artificial neural network (ANN) based model with feature selection using the principal component analysis (PCA) technique for malware detection. The effectiveness of the approach has been successfully demonstrated with the application in PDF malware detection. A varying number of principal components is examined in the comparative study. Our evaluation shows that the model with PCA can significantly reduce feature redundancy and learning time with minimum impact on data information loss, as confirmed by both training and testing results based on around 105,000 real-world PDF documents. Of the evaluated models using PCA, the model with 32 principal feature components exhibits very similar training accuracy to the model using the 48 original features, resulting in around 33% dimensionality reduction and 22% less learning time. The testing results further confirm the effectiveness and show that the model is able to achieve 93.17% true positive rate (TPR) while maintaining the same low false positive rate (FPR) of 0.08% as the case when no feature selection is applied, which significantly outperforms all evaluated seven well known commercial antivirus (AV) scanners of which the best scanner only has a TPR of 84.53%.
Tasks	Dimensionality Reduction, Feature Selection, Malware Detection
Published	2019-02-10
URL	http://arxiv.org/abs/1902.03639v1
PDF	http://arxiv.org/pdf/1902.03639v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-with-feature-selection-using
Repo
Framework

Federated Adversarial Domain Adaptation


Title	Federated Adversarial Domain Adaptation
Authors	Xingchao Peng, Zijun Huang, Yizhe Zhu, Kate Saenko
Abstract	Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc. Yet models trained with federated learning can still fail to generalize to new devices due to the problem of domain shift. Domain shift occurs when the labeled data collected by source nodes statistically differs from the target node’s unlabeled data. In this work, we present a principled approach to the problem of federated domain adaptation, which aims to align the representations learned among the different nodes with the data distribution of the target node. Our approach extends adversarial adaptation techniques to the constraints of the federated setting. In addition, we devise a dynamic attention mechanism and leverage feature disentanglement to enhance knowledge transfer. Empirically, we perform extensive experiments on several image and text classification tasks and show promising results under unsupervised federated domain adaptation setting.
Tasks	Domain Adaptation, Text Classification, Transfer Learning
Published	2019-11-05
URL	https://arxiv.org/abs/1911.02054v2
PDF	https://arxiv.org/pdf/1911.02054v2.pdf
PWC	https://paperswithcode.com/paper/federated-adversarial-domain-adaptation
Repo
Framework

VILD: Variational Imitation Learning with Diverse-quality Demonstrations


Title	VILD: Variational Imitation Learning with Diverse-quality Demonstrations
Authors	Voot Tangkaratt, Bo Han, Mohammad Emtiyaz Khan, Masashi Sugiyama
Abstract	The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs. IL in such situations can be challenging, especially when the level of demonstrators’ expertise is unknown. We propose a new IL method called \underline{v}ariational \underline{i}mitation \underline{l}earning with \underline{d}iverse-quality demonstrations (VILD), where we explicitly model the level of demonstrators’ expertise with a probabilistic graphical model and estimate it along with a reward function. We show that a naive approach to estimation is not suitable to large state and action spaces, and fix its issues by using a variational approach which can be easily implemented using existing reinforcement learning methods. Experiments on continuous-control benchmarks demonstrate that VILD outperforms state-of-the-art methods. Our work enables scalable and data-efficient IL under more realistic settings than before.
Tasks	Continuous Control, Imitation Learning
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06769v1
PDF	https://arxiv.org/pdf/1909.06769v1.pdf
PWC	https://paperswithcode.com/paper/vild-variational-imitation-learning-with
Repo
Framework

Learning Boolean Circuits with Neural Networks


Title	Learning Boolean Circuits with Neural Networks
Authors	Eran Malach, Shai Shalev-Shwartz
Abstract	While on some natural distributions, neural-networks are trained efficiently using gradient-based algorithms, it is known that learning them is computationally hard in the worst-case. To separate hard from easy to learn distributions, we observe the property of local correlation: correlation between local patterns of the input and the target label. We focus on learning deep neural-networks using a gradient-based algorithm, when the target function is a tree-structured Boolean circuit. We show that in this case, the existence of correlation between the gates of the circuit and the target label determines whether the optimization succeeds or fails. Using this result, we show that neural-networks can learn the (log n)-parity problem for most product distributions. These results hint that local correlation may play an important role in separating easy/hard to learn distributions. We also obtain a novel depth separation result, in which we show that a shallow network cannot express some functions, while there exists an efficient gradient-based algorithm that can learn the very same functions using a deep network. The negative expressivity result for shallow networks is obtained by a reduction from results in communication complexity, that may be of independent interest.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11923v2
PDF	https://arxiv.org/pdf/1910.11923v2.pdf
PWC	https://paperswithcode.com/paper/learning-boolean-circuits-with-neural
Repo
Framework

User Profile Feature-Based Approach to Address the Cold Start Problem in Collaborative Filtering for Personalized Movie Recommendation


Title	User Profile Feature-Based Approach to Address the Cold Start Problem in Collaborative Filtering for Personalized Movie Recommendation
Authors	Lasitha Uyangoda, Supunmali Ahangama, Tharindu Ranasinghe
Abstract	A huge amount of user generated content related to movies is created with the popularization of web 2.0. With these continues exponential growth of data, there is an inevitable need for recommender systems as people find it difficult to make informed and timely decisions. Movie recommendation systems assist users to find the next interest or the best recommendation. In this proposed approach the authors apply the relationship of user feature-scores derived from user-item interaction via ratings to optimize the prediction algorithm’s input parameters used in the recommender system to improve the accuracy of predictions when there are less past user records. This addresses a major drawback in collaborative filtering, the cold start problem by showing an improvement of 8.4% compared to the base collaborative filtering algorithm. The user-feature generation and evaluation of the system is carried out using the ‘MovieLens 100k dataset’. The proposed system can be generalized to other domains as well.
Tasks	Recommendation Systems
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00365v1
PDF	https://arxiv.org/pdf/1906.00365v1.pdf
PWC	https://paperswithcode.com/paper/190600365
Repo
Framework

Machine Learning for Data-Driven Movement Generation: a Review of the State of the Art


Title	Machine Learning for Data-Driven Movement Generation: a Review of the State of the Art
Authors	Omid Alemi, Philippe Pasquier
Abstract	The rise of non-linear and interactive media such as video games has increased the need for automatic movement animation generation. In this survey, we review and analyze different aspects of building automatic movement generation systems using machine learning techniques and motion capture data. We cover topics such as high-level movement characterization, training data, features representation, machine learning models, and evaluation methods. We conclude by presenting a discussion of the reviewed literature and outlining the research gaps and remaining challenges for future work.
Tasks	Motion Capture
Published	2019-03-20
URL	http://arxiv.org/abs/1903.08356v1
PDF	http://arxiv.org/pdf/1903.08356v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-data-driven-movement
Repo
Framework

Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile


Title	Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile
Authors	Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng
Abstract	Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word given the sequence of previous words. Therefore, statistical language models, i.e.~n-grams based models, have been extensively used on this task in real application. However, the characteristics of extremely different typing behaviors usually lead to serious sparsity problem, even n-gram with smoothing will fail. A reasonable approach to tackle this problem is to use the recently proposed neural models, such as probabilistic neural language model, recurrent neural network and word2vec. They can leverage more semantically similar words for estimating the probability. However, there is no conclusion on which approach of the two will work better in real application. In this paper, we conduct an extensive empirical study to show the differences between statistical and neural language models. The experimental results show that the two different approach have individual advantages, and a hybrid approach will bring a significant improvement.
Tasks	Language Modelling
Published	2019-07-09
URL	https://arxiv.org/abs/1907.05340v1
PDF	https://arxiv.org/pdf/1907.05340v1.pdf
PWC	https://paperswithcode.com/paper/neural-or-statistical-an-empirical-study-on
Repo
Framework

Estimating Numerical Distributions under Local Differential Privacy


Title	Estimating Numerical Distributions under Local Differential Privacy
Authors	Zitao Li, Tianhao Wang, Milan Lopuhaä-Zwakenberg, Boris Skoric, Ninghui Li
Abstract	When collecting information, local differential privacy (LDP) relieves the concern of privacy leakage from users’ perspective, as user’s private information is randomized before sent to the aggregator. We study the problem of recovering the distribution over a numerical domain while satisfying LDP. While one can discretize a numerical domain and then apply the protocols developed for categorical domains, we show that taking advantage of the numerical nature of the domain results in better trade-off of privacy and utility. We introduce a new reporting mechanism, called the square wave SW mechanism, which exploits the numerical nature in reporting. We also develop an Expectation Maximization with Smoothing (EMS) algorithm, which is applied to aggregated histograms from the SW mechanism to estimate the original distributions. Extensive experiments demonstrate that our proposed approach, SW with EMS, consistently outperforms other methods in a variety of utility metrics.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01051v1
PDF	https://arxiv.org/pdf/1912.01051v1.pdf
PWC	https://paperswithcode.com/paper/estimating-numerical-distributions-under
Repo
Framework