April 2, 2020

3403 words 16 mins read

Paper Group ANR 100

Data and Model Dependencies of Membership Inference Attack. Block Switching: A Stochastic Approach for Deep Learning Security. Cell Mechanics Based Computational Classification of Red Blood Cells Via Machine Intelligence Applied to Morpho-Rheological Markers. Semantic Robustness of Models of Source Code. Fine-grained Image-to-Image Transformation t …

Data and Model Dependencies of Membership Inference Attack


Title	Data and Model Dependencies of Membership Inference Attack
Authors	Shakila Mahjabin Tonni, Farhad Farokhi, Dinusha Vatsalan, Dali Kaafar
Abstract	Machine Learning (ML) techniques are used by most data-driven organisations to extract insights. Machine-learning-as-a-service (MLaaS), where models are trained on potentially sensitive user data and then queried by external parties are becoming a reality. However, recently, these systems have been shown to be vulnerable to Membership Inference Attacks (MIA), where a target’s data can be inferred to belong or not to the training data. While the key factors for the success of MIA have not been fully understood, existing defence mechanisms only consider the model-specific properties. We investigate the impact of both the data and ML model properties on the vulnerability of ML techniques to MIA. Our analysis indicates a strong relationship between the MIA success and the properties of the data in use, such as the data size and balance between the classes as well as the model properties including the fairness in prediction and the mutual information between the records and the model’s parameters. We then propose new approaches to protect ML models from MIA by using several properties, e.g. the model’s fairness and mutual information between the records and the model’s parameters as regularizers, which reduces the attack accuracy by 25%, while yielding a fairer and a better performing ML model.
Tasks	Inference Attack
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06856v1
PDF	https://arxiv.org/pdf/2002.06856v1.pdf
PWC	https://paperswithcode.com/paper/data-and-model-dependencies-of-membership
Repo
Framework

Block Switching: A Stochastic Approach for Deep Learning Security


Title	Block Switching: A Stochastic Approach for Deep Learning Security
Authors	Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin
Abstract	Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions, while maintain imperceptible to human vision system. In this paper, we introduce Block Switching (BS), a defense strategy against adversarial attacks based on stochasticity. BS replaces a block of model layers with multiple parallel channels, and the active channel is randomly assigned in the run time hence unpredictable to the adversary. We show empirically that BS leads to a more dispersed input gradient distribution and superior defense effectiveness compared with other stochastic defenses such as stochastic activation pruning (SAP). Compared to other defenses, BS is also characterized by the following features: (i) BS causes less test accuracy drop; (ii) BS is attack-independent and (iii) BS is compatible with other defenses and can be used jointly with others.
Tasks
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07920v1
PDF	https://arxiv.org/pdf/2002.07920v1.pdf
PWC	https://paperswithcode.com/paper/block-switching-a-stochastic-approach-for
Repo
Framework

Cell Mechanics Based Computational Classification of Red Blood Cells Via Machine Intelligence Applied to Morpho-Rheological Markers


Title	Cell Mechanics Based Computational Classification of Red Blood Cells Via Machine Intelligence Applied to Morpho-Rheological Markers
Authors	Yan Ge, Philipp Rosendahl, Claudio Durán, Nicole Töpfner, Sara Ciucci, Jochen Guck, Carlo Vittorio Cannistraci
Abstract	Despite fluorescent cell-labelling being widely employed in biomedical studies, some of its drawbacks are inevitable, with unsuitable fluorescent probes or probes inducing a functional change being the main limitations. Consequently, the demand for and development of label-free methodologies to classify cells is strong and its impact on precision medicine is relevant. Towards this end, high-throughput techniques for cell mechanical phenotyping have been proposed to get a multidimensional biophysical characterization of single cells. With this motivation, our goal here is to investigate the extent to which an unsupervised machine learning methodology, which is applied exclusively on morpho-rheological markers obtained by real-time deformability and fluorescence cytometry (RT-FDC), can address the difficult task of providing label-free discrimination of reticulocytes from mature red blood cells. We focused on this problem, since the characterization of reticulocytes (their percentage and cellular features) in the blood is vital in multiple human disease conditions, especially bone-marrow disorders such as anemia and leukemia. Our approach reports promising label-free results in the classification of reticulocytes from mature red blood cells, and it represents a step forward in the development of high-throughput morpho-rheological-based methodologies for the computational categorization of single cells. Besides, our methodology can be an alternative but also a complementary method to integrate with existing cell-labelling techniques.
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00009v1
PDF	https://arxiv.org/pdf/2003.00009v1.pdf
PWC	https://paperswithcode.com/paper/cell-mechanics-based-computational
Repo
Framework

Semantic Robustness of Models of Source Code


Title	Semantic Robustness of Models of Source Code
Authors	Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas Reps
Abstract	Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem in the context of models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. We define a natural notion of robustness, $k$-transformation robustness, in which an adversary performs up to $k$ semantics-preserving transformations to an input program. We show how to train robust models using an adversarial training objective inspired by that of Madry et al. (2018) for continuous domains. We implement an extensible framework for adversarial training over source code, and conduct a thorough evaluation on a number of datasets and two different architectures. Our results show (1) the increase in robustness following adversarial training, (2) the ability of training on weak adversaries to provide robustness to attacks by stronger adversaries, and (3) the shift in attribution focus of adversarially trained models towards semantic vs. syntactic features.
Tasks
Published	2020-02-07
URL	https://arxiv.org/abs/2002.03043v1
PDF	https://arxiv.org/pdf/2002.03043v1.pdf
PWC	https://paperswithcode.com/paper/semantic-robustness-of-models-of-source-code
Repo
Framework

Fine-grained Image-to-Image Transformation towards Visual Recognition


Title	Fine-grained Image-to-Image Transformation towards Visual Recognition
Authors	Wei Xiong, Yutong He, Yixuan Zhang, Wenhan Luo, Lin Ma, Jiebo Luo
Abstract	Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image transformation tasks with large deformation in poses, viewpoints or scales while preserving the identity, such as face rotation and object viewpoint morphing. In this paper, we aim at transforming an image with a fine-grained category to synthesize new images that preserve the identity of the input image, which can thereby benefit the subsequent fine-grained image recognition and few-shot learning tasks. The generated images, transformed with large geometric deformation, do not necessarily need to be of high visual quality, but are required to maintain as much identity information as possible. To this end, we adopt a model based on generative adversarial networks to disentangle the identity related and unrelated factors of an image. In order to preserve the fine-grained contextual details of the input image during the deformable transformation, a constrained nonalignment connection method is proposed to construct learnable highways between intermediate convolution blocks in the generator. Moreover, an adaptive identity modulation mechanism is proposed to effectively transfer the identity information into the output image. Extensive experiments on the CompCars and Multi-PIE datasets demonstrate that our model preserves the identity of the generated images much better than the state-of-the-art image-to-image transformation models, and as a result significantly boosts the visual recognition performance in fine-grained few-shot learning.
Tasks	Few-Shot Learning, Fine-Grained Image Recognition
Published	2020-01-12
URL	https://arxiv.org/abs/2001.03856v1
PDF	https://arxiv.org/pdf/2001.03856v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-image-to-image-transformation
Repo
Framework

Revisit to the Inverse Exponential Radon Transform


Title	Revisit to the Inverse Exponential Radon Transform
Authors	Jason You
Abstract	This revisit gives a survey on the analytical methods for the inverse exponential Radon transform which has been investigated in the past three decades from both mathematical interests and medical applications such as nuclear medicine emission imaging. The derivation of the classical inversion formula is through the recent argument developed for the inverse attenuated Radon transform. That derivation allows the exponential parameter to be a complex constant, which is useful to other applications such as magnetic resonance imaging and tensor field imaging. The survey also includes the new technique of using the finite Hilbert transform to handle the exact reconstruction from 180 degree data. Special treatment has been paid on two practically important subjects. One is the exact reconstruction from partial measurements such as half-scan and truncated-scan data, and the other is the reconstruction from diverging-beam data. The noise propagation in the reconstruction is touched upon with more heuristic discussions than mathematical inference. The numerical realizations of several classical reconstruction algorithms are included. In the conclusion, several topics are discussed for more investigations in the future.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01622v1
PDF	https://arxiv.org/pdf/2002.01622v1.pdf
PWC	https://paperswithcode.com/paper/revisit-to-the-inverse-exponential-radon
Repo
Framework

Detection of Diabetic Anomalies in Retinal Images using Morphological Cascading Decision Tree


Title	Detection of Diabetic Anomalies in Retinal Images using Morphological Cascading Decision Tree
Authors	Faisal Ghaffar, Sarwar Khan, Bunyarit Uyyanonvara, Chanjira Sinthanayothin, Hirohiko Kaneko
Abstract	This research aims to develop an efficient system for screening of diabetic retinopathy. Diabetic retinopathy is the major cause of blindness. Severity of diabetic retinopathy is recognized by some features, such as blood vessel area, exudates, haemorrhages and microaneurysms. To grade the disease the screening system must efficiently detect these features. In this paper we are proposing a simple and fast method for detection of diabetic retinopathy. We do pre-processing of grey-scale image and find all labelled connected components (blobs) in an image regardless of whether it is haemorrhages, exudates, vessels, optic disc or anything else. Then we apply some constraints such as compactness, area of blob, intensity and contrast for screening of candidate connectedcomponent responsible for diabetic retinopathy. We obtain our final results by doing some post processing. The results are compared with ground truths. Performance is measured by finding the recall (sensitivity). We took 10 images of dimension 500 * 752. The mean recall is 90.03%.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.01953v1
PDF	https://arxiv.org/pdf/2001.01953v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-diabetic-anomalies-in-retinal
Repo
Framework

The Final Frontier: Deep Learning in Space


Title	The Final Frontier: Deep Learning in Space
Authors	Vivek Kothari, Edgar Liberis, Nicholas D. Lane
Abstract	Machine learning, particularly deep learning, is being increasing utilised in space applications, mirroring the groundbreaking success in many earthbound problems. Deploying a space device, e.g. a satellite, is becoming more accessible to small actors due to the development of modular satellites and commercial space launches, which fuels further growth of this area. Deep learning’s ability to deliver sophisticated computational intelligence makes it an attractive option to facilitate various tasks on space devices and reduce operational costs. In this work, we identify deep learning in space as one of development directions for mobile and embedded machine learning. We collate various applications of machine learning to space data, such as satellite imaging, and describe how on-device deep learning can meaningfully improve the operation of a spacecraft, such as by reducing communication costs or facilitating navigation. We detail and contextualise compute platform of satellites and draw parallels with embedded systems and current research in deep learning for resource-constrained environments.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.10362v2
PDF	https://arxiv.org/pdf/2001.10362v2.pdf
PWC	https://paperswithcode.com/paper/the-final-frontier-deep-learning-in-space
Repo
Framework

PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression


Title	PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression
Authors	Zheng Ge, Zequn Jie, Xin Huang, Rong Xu, Osamu Yoshie
Abstract	Detecting human bodies in highly crowded scenes is a challenging problem. Two main reasons result in such a problem: 1). weak visual cues of heavily occluded instances can hardly provide sufficient information for accurate detection; 2). heavily occluded instances are easier to be suppressed by Non-Maximum-Suppression (NMS). To address these two issues, we introduce a variant of two-stage detectors called PS-RCNN. PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out. After that, PS-RCNN utilizes another R-CNN module specialized in heavily occluded human detection (referred as S-RCNN) to detect the rest missed objects by P-RCNN. Final results are the ensemble of the outputs from these two R-CNNs. Moreover, we introduce a High Resolution RoI Align (HRRA) module to retain as much of fine-grained features of visible parts of the heavily occluded humans as possible. Our PS-RCNN significantly improves recall and AP by 4.49% and 2.92% respectively on CrowdHuman, compared to the baseline. Similar improvements on Widerperson are also achieved by the PS-RCNN.
Tasks	Human Detection
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07080v1
PDF	https://arxiv.org/pdf/2003.07080v1.pdf
PWC	https://paperswithcode.com/paper/ps-rcnn-detecting-secondary-human-instances
Repo
Framework

Socially intelligent task and motion planning for human-robot interaction


Title	Socially intelligent task and motion planning for human-robot interaction
Authors	Andrea Frank, Laurel Riek
Abstract	As social beings, much human behavior is predicated on social context - the ambient social state that includes cultural norms, social signals, individual preferences, etc. In this paper, we propose a socially-aware task and motion planning algorithm that considers social context to generate appropriate and effective plans in human social environments (HSEs). The key strength of our proposed approach is that it explicitly models how potential actions not only affect objective cost, but also transform the social context in which it plans and acts. We investigate strategies to limit the complexity of our algorithm, so that our planner will remain tractable for mobile platforms in complex HSEs like hospitals and factories. The planner will also consider the relative importance and urgency of its tasks, which it uses to determine when it is and is not appropriate to violate social expectations to achieve its objective. This social awareness will allow robots to understand a fundamental rule of society: just because something makes your job easier, does not make it the right thing to do! To our knowledge, the proposed work is the first task and motion planning approach that supports socially intelligent robot policy for HSEs. Through this ongoing work, robots will be able to understand, respect, and leverage social context accomplish tasks both acceptably and effectively in HSEs.
Tasks	Motion Planning
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08398v1
PDF	https://arxiv.org/pdf/2001.08398v1.pdf
PWC	https://paperswithcode.com/paper/socially-intelligent-task-and-motion-planning
Repo
Framework

Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning


Title	Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning
Authors	Samaneh Hosseini Semnani, Hugh Liu, Michael Everett, Anton de Ruiter, Jonathan P. How
Abstract	This paper introduces a hybrid algorithm of deep reinforcement learning (RL) and Force-based motion planning (FMP) to solve distributed motion planning problem in dense and dynamic environments. Individually, RL and FMP algorithms each have their own limitations. FMP is not able to produce time-optimal paths and existing RL solutions are not able to produce collision-free paths in dense environments. Therefore, we first tried improving the performance of recent RL approaches by introducing a new reward function that not only eliminates the requirement of a pre supervised learning (SL) step but also decreases the chance of collision in crowded environments. That improved things, but there were still a lot of failure cases. So, we developed a hybrid approach to leverage the simpler FMP approach in stuck, simple and high-risk cases, and continue using RL for normal cases in which FMP can’t produce optimal path. Also, we extend GA3C-CADRL algorithm to 3D environment. Simulation results show that the proposed algorithm outperforms both deep RL and FMP algorithms and produces up to 50% more successful scenarios than deep RL and up to 75% less extra time to reach goal than FMP.
Tasks	Motion Planning
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06627v1
PDF	https://arxiv.org/pdf/2001.06627v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-motion-planning-for-dense-and
Repo
Framework

No-Regret Prediction in Marginally Stable Systems


Title	No-Regret Prediction in Marginally Stable Systems
Authors	Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
Abstract	We consider the problem of online prediction in a marginally stable linear dynamical system subject to bounded adversarial or (non-isotropic) stochastic perturbations. This poses two challenges. Firstly, the system is in general unidentifiable, so recent and classical results on parameter recovery do not apply. Secondly, because we allow the system to be marginally stable, the state can grow polynomially with time; this causes standard regret bounds in online convex optimization to be vacuous. In spite of these challenges, we show that the online least-squares algorithm achieves sublinear regret (improvable to polylogarithmic in the stochastic setting), with polynomial dependence on the system’s parameters. This requires a refined regret analysis, including a structural lemma showing the current state of the system to be a small linear combination of past states, even if the state grows polynomially. By applying our techniques to learning an autoregressive filter, we also achieve logarithmic regret in the partially observed setting under Gaussian noise, with polynomial dependence on the memory of the associated Kalman filter.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02064v2
PDF	https://arxiv.org/pdf/2002.02064v2.pdf
PWC	https://paperswithcode.com/paper/no-regret-prediction-in-marginally-stable
Repo
Framework

Recursed is not Recursive: A Jarring Result


Title	Recursed is not Recursive: A Jarring Result
Authors	Erik Demaine, Justin Kopinsky, Jayson Lynch
Abstract	Recursed is a 2D puzzle platform video game featuring treasure chests that, when jumped into, instantiate a room that can later be exited (similar to function calls), optionally generating a \jar that returns back to that room (similar to continuations). We prove that Recursed is RE-complete and thus undecidable (not recursive) by a reduction from the Post Correspondence Problem. Our reduction is “practical”: the reduction from PCP results in fully playable levels that abide by all constraints governing levels (including the 15x20 room size) designed for the main game. Our reduction is also “efficient”: a Turing machine can be simulated by a Recursed level whose size is linear in the encoding size of the Turing machine and whose solution length is polynomial in the running time of the Turing machine.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05131v1
PDF	https://arxiv.org/pdf/2002.05131v1.pdf
PWC	https://paperswithcode.com/paper/recursed-is-not-recursive-a-jarring-result
Repo
Framework

SANST: A Self-Attentive Network for Next Point-of-Interest Recommendation


Title	SANST: A Self-Attentive Network for Next Point-of-Interest Recommendation
Authors	Qianyu Guo, Jianzhong Qi
Abstract	Next point-of-interest (POI) recommendation aims to offer suggestions on which POI to visit next, given a user’s POI visit history. This problem has a wide application in the tourism industry, and it is gaining an increasing interest as more POI check-in data become available. The problem is often modeled as a sequential recommendation problem to take advantage of the sequential patterns of user check-ins, e.g., people tend to visit Central Park after The Metropolitan Museum of Art in New York City. Recently, self-attentive networks have been shown to be both effective and efficient in general sequential recommendation problems, e.g., to recommend products, video games, or movies. Directly adopting self-attentive networks for next POI recommendation, however, may produce sub-optimal recommendations. This is because vanilla self-attentive networks do not consider the spatial and temporal patterns of user check-ins, which are two critical features in next POI recommendation. To address this limitation, in this paper, we propose a model named SANST that incorporates spatio-temporal patterns of user check-ins into self-attentive networks. To incorporate the spatial patterns, we encode the relative positions of POIs into their embeddings before feeding the embeddings into the self-attentive network. To incorporate the temporal patterns, we discretize the time of POI check-ins and model the temporal relationship between POI check-ins by a relation-aware self-attention module. We evaluate the performance of our SANST model with three real-world datasets. The results show that SANST consistently outperforms the state-of-theart models, and the advantage in nDCG@10 is up to 13.65%.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.10379v1
PDF	https://arxiv.org/pdf/2001.10379v1.pdf
PWC	https://paperswithcode.com/paper/sanst-a-self-attentive-network-for-next-point
Repo
Framework

DALC: Distributed Automatic LSTM Customization for Fine-Grained Traffic Speed Prediction


Title	DALC: Distributed Automatic LSTM Customization for Fine-Grained Traffic Speed Prediction
Authors	Ming-Chang Lee, Jia-Chun Lin
Abstract	Over the past decade, several approaches have been introduced for short-term traffic prediction. However, providing fine-grained traffic prediction for large-scale transportation networks where numerous detectors are geographically deployed to collect traffic data is still an open issue. To address this issue, in this paper, we formulate the problem of customizing an LSTM model for a single detector into a finite Markov decision process and then introduce an Automatic LSTM Customization (ALC) algorithm to automatically customize an LSTM model for a single detector such that the corresponding prediction accuracy can be as satisfactory as possible and the time consumption can be as low as possible. Based on the ALC algorithm, we introduce a distributed approach called Distributed Automatic LSTM Customization (DALC) to customize an LSTM model for every detector in large-scale transportation networks. Our experiment demonstrates that the DALC provides higher prediction accuracy than several approaches provided by Apache Spark MLlib.
Tasks	Traffic Prediction
Published	2020-01-24
URL	https://arxiv.org/abs/2001.09821v2
PDF	https://arxiv.org/pdf/2001.09821v2.pdf
PWC	https://paperswithcode.com/paper/dalc-distributed-automatic-lstm-customization
Repo
Framework