Computer Sciences Commons^™

Memoryranger Prevents Highjacking File_Object Structures In Windows Kernel, Igor Korkin

Journal of Digital Forensics, Security and Law

Windows OS kernel memory is one of the main targets of cyber-attacks. By launching such attacks, hackers are succeeding in process privilege escalation and tampering users’ data by accessing kernel-mode memory. This paper considers a new example of such an attack, which results in access to the files opened in an exclusive mode. Windows built-in security features prevent such a legal access, but attackers can circumvent them by patching dynamically allocated objects. The research shows that the newest Windows 10 x64 is vulnerable to this attack. The paper provides an example of using MemoryRanger, a hypervisor- based solution to prevent …

Generating Expensive Relationship Features From Cheap Objects, Xiaogang Wang, Qianru Sun, Tat-Seng Chua, Marcelo Ang

Research Collection School Of Computing and Information Systems

We investigate the problem of object relationship classification of visual scenes. For a relationship object1-predicate-object2 that captures the object interaction, its representation is composed by the combination of object1 and object2 features. As a result, relationship classification models usually bias to the frequent objects, leading to poor generalization to rare or unseen objects. Inspired by the data augmentation methods, we propose a novel Semantic Transform Generative Adversarial Network (ST-GAN) that synthesizes relationship features for rare objects, conditioned on the features from random instances of the objects. Specifically, ST-GAN essentially offers a semantic transform function from cheap object features to expensive …

Using Vibrations From A Smartring As An Out-Of-Band Channel For Sharing Secret Keys, Sougata Sen, Varun Mishra, David Kotz

Dartmouth Scholarship

With the rapid growth in the number of Internet of Things (IoT) devices with wireless communication capabilities, and sensitive information collection capabilities, it is becoming increasingly necessary to ensure that these devices communicate securely with only authorized devices. A major requirement of this secure communication is to ensure that both the devices share a secret, which can be used for secure pairing and encrypted communication. Manually imparting this secret to these devices becomes an unnecessary overhead, especially when the device interaction is transient. In this work, we empirically investigate the possibility of using an out-of-band communication channel – vibration, generated …

Rotation Invariant Convolutions For 3d Point Clouds Deep Learning, Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung

Research Collection School Of Computing and Information Systems

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the …

Edgesense: Edge-Mediated Spatial-Temporal Crowdsensing, Sijia Yang, Jiang Bian, Licheng Wang, Haojin Zhu, Yanjie Fu, Haoyi Xiong

Computer Science Faculty Research & Creative Works

Edge computing recently is increasingly popular due to the growth of data size and the need of sensing with the reduced center. Based on Edge computing architecture, we propose a novel crowdsensing framework called Edge-Mediated Spatial-Temporal Crowdsensing. This algorithm targets on receiving the environment information such as air pollution, temperature, and traffic flow in some parts of the goal area, and does not aggregate sensor data with its location information. Specifically, EdgeSense works on top of a secured peer-To-peer network consisted of participants and propose a novel Decentralized Spatial-Temporal Crowdsensing framework based on Parallelized Stochastic Gradient Descent. To approximate the …

Preference Learning And Similarity Learning Perspectives On Personalized Recommendation, Duy Dung Le

Dissertations and Theses Collection (Open Access)

Personalized recommendation, whose objective is to generate a limited list of items (e.g., products on Amazon, movies on Netflix, or pins on Pinterest, etc.) for each user, has gained extensive attention from both researchers and practitioners in the last decade. The necessity of personalized recommendation is driven by the explosion of available options online, which makes it difficult, if not downright impossible, for each user to investigate every option. Product and service providers rely on recommendation algorithms to identify manageable number of the most likely or preferred options to be presented to each user. Also, due to the limited screen …

Exploiting Approximation, Caching And Specialization To Accelerate Vision Sensing Applications, Nguyen Loc Huynh

Dissertations and Theses Collection (Open Access)

Over the past few years, deep learning has emerged as state-of-the-art solutions for many challenging computer vision tasks such as face recognition, object detection, etc. Despite of its outstanding performance, deep neural networks (DNNs) are computational intensive, which prevent them to be widely adopted on billions of mobile and embedded devices with scarce resources. To address that limitation, we
focus on building systems and optimization algorithms to accelerate those models, making them more computational-efficient.
First, this thesis explores the computational capabilities of different existing processors (or co-processors) on modern mobile devices. It recognizes that by leveraging the mobile Graphics Processing …

Predictors Of Ransomware From Binary Analysis, Aaron M. Otis

Master's Theses

Ransomware, a type of malware that extorts payment from a victim by encrypting her data, is a growing threat that is becoming more sophisticated with each generation. Attackers have shifted from targeting individuals to entire organizations, raising extortions from hundreds of dollars to hundreds of thousands of dollars. In this work, we analyze a variety of ransomware and benign software binaries in order to identify indicators that may be used to detect ransomware. We find that several combinations of strings, cryptographic constants, and a large number loops are key indicators useful for detecting ransomware.

Exploring The Uncanny Valley Effect In Vr/Ar, Ting Yan

Dartmouth College Master’s Theses

This research is focused on the Uncanny Valley Effect of humanoid avatars, in a Virtual Reality (VR) /Augmented Reality (AR) environment. We designed and conducted a user study to observe people's reaction and behavior when interacting with virtual avatars of different levels of human likeness in VR and AR. Subjective surveys and objective measurement including EEG (Electroencephalogram), GSR (Galvanic Skin Response), Pupil Dilation sensors are used for quantification. Our result shows that, overall, in AR, people tend to like more human-like avatars, and users are more sensitive to facial expressions compared to body resemblance, especially on highly human likeness avatars. …

Predicting The Hardness Of Turf Surfaces From A Soil Moisture Sensor Using Iot Technologies, Ann Marie Mckeon

Other

In horseracing, “the going” is a term to describe the racetrack ground conditions. In Ireland presently, a groundskeeper or course clerk walks the racecourse poking it with a blackthorn stick, assesses conditions, and declares the going – it is a subjective measurement.

This thesis will propose using remote low-cost soil moisture sensors to gather high frequency data about the soil water content in the ground and to enable informed decisions to be made. This will remove the subjective element from the ground hardness, and look at the data in an objective way.

The soil moisture sensor will systematically collect high …

Estimating Distributed Representation Performance In Disaster-Related Social Media Classification, Pallavi Jain, Robert J. Ross, Bianca Schoen-Phelan

Conference papers

This paper examines the effectiveness of a range of pre-trained language representations in order to determine the informativeness and information type of social media in the event of natural or man-made disasters. Within the context of disaster tweet analysis, we aim to accurately analyse tweets while minimising both false positive and false negatives in the automated information analysis. The investigation is performed across a number of well known disaster-related twitter datasets. Models that are built from pre-trained word embeddings from Word2Vec, GloVe, ELMo and BERT are used for performance evaluation. Given the relative ubiquity of BERT as a standout language …

Ion Software-Defined Radio Metadata Standard Final Report, Sanjeev Gunawardena, Alexander Rugamer, Muhammad Subhan Hameed, Markel Arizabaleta, Thomas Pany, Javier Arribas

Faculty Publications

The ION GNSS SDR Metadata Standard describes the formatting and other essential PNT-related parameters of sampled data streams and files. This allows processors to seamlessly consume such data without the need to input these parameters manually. The technical development phase of the initial version of the standard has now been deemed complete and is currently undergoing the last remaining procedural steps towards adoption as a formal standard by the Institute of Navigation. This paper reports on the activities of the working group since September 2018 and summarizes the final products of the standard. It also reports on examples of early …

A Light Weight Smartphone Based Human Activity Recognition System With High Accuracy, Md. O. Gani, Taskina Fayezeen, Richard J. Povinelli, Roger O. Smith, Muhammad Arif, Ahmed Kattan, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

With the pervasive use of smartphones, which contain numerous sensors, data for modeling human activity is readily available. Human activity recognition is an important area of research because it can be used in context-aware applications. It has significant influence in many other research areas and applications including healthcare, assisted living, personal fitness, and entertainment. There has been a widespread use of machine learning techniques in wearable and smartphone based human activity recognition. Despite being an active area of research for more than a decade, most of the existing approaches require extensive computation to extract feature, train model, and recognize activities. …

Efficient Oblivious Transfer With Membership Verification, Weiwei Liu, Dazhi Sun, Yangguang Tian

Research Collection School Of Computing and Information Systems

In this article, we introduce a new concept of oblivious transfer with membership verification that allows any legitimate group users to obtain services from a service provider in an oblivious manner. We present two oblivious transfer with membership verification schemes, differing in design. In the first scheme, a trusted group manager issues credentials for a pre-determined group of users so that the group of users with a valid group credential can obtain services from the service provider, while the choices made by group users remain oblivious to the service provider. The second scheme avoids the trusted group manager, which allows …

Lightweight Fine-Grained Search Over Encrypted Data In Fog Computing, Yinbin Miao, Jianfeng Ma, Ximeng Liu, Jian Weng, Hongwei Li, Hui Li

Research Collection School Of Computing and Information Systems

Fog computing, as an extension of cloud computing, outsources the encrypted sensitive data to multiple fog nodes on the edge of Internet of Things (IoT) to decrease latency and network congestion. However, the existing ciphertext retrieval schemes rarely focus on the fog computing environment and most of them still impose high computational and storage overhead on resource-limited end users. In this paper, we first present a Lightweight Fine-Grained ciphertexts Search (LFGS) system in fog computing by extending Ciphertext-Policy Attribute-Based Encryption (CP-ABE) and Searchable Encryption (SE) technologies, which can achieve fine-grained access control and keyword search simultaneously. The LFGS can shift …

Spatio-Temporal Analysis And Prediction Of Cellular Traffic In Metropolis, Xu Wang, Zimu Zhou, Fu Xiao, Kai Xing, Zheng Yang, Yunhao Liu, Chunyi Peng

Research Collection School Of Computing and Information Systems

Understanding and predicting cellular traffic at large-scale and fine-granularity is beneficial and valuable to mobile users, wireless carriers and city authorities. Predicting cellular traffic in modern metropolis is particularly challenging because of the tremendous temporal and spatial dynamics introduced by diverse user Internet behaviours and frequent user mobility citywide. In this paper, we characterize and investigate the root causes of such dynamics in cellular traffic through a big cellular usage dataset covering 1.5 million users and 5,929 cell towers in a major city of China. We reveal intensive spatiotemporal dependency even among distant cell towers, which is largely overlooked in …

Interlocking Structure Design And Assembly, Yinan Zhang

Dartmouth College Ph.D Dissertations

Many objects in our life are not manufactured as whole rigid pieces. Instead, smaller components are made to be later assembled into larger structures. Chairs are assembled from wooden pieces, cabins are made of logs, and buildings are constructed from bricks. These components are commonly designed by many iterations of human thinking. In this report, we will look at a few problems related to interlocking components design and assembly. Given an atomic object, how can we design a package that holds the object firmly without a gap in-between? How many pieces should the package be partitioned into? How can we …

Output-Constrained Control Of Nonaffine Multiagent Systems With Partially Unknown Control Directions, Bo Fan, Qinmin Yang, Sarangapani Jagannathan, Youxian Sun

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, an output-constrained control algorithm is presented for the consensus control of a class of unknown nonaffine multiagent systems (MASs) with partially unknown control directions. Our contribution includes a step forward beyond the usual consensus stabilization result to show that the outputs of agents remain within user-defined time-varying constraints. To achieve the new results, an error transformation technique is established to generate an equivalent MAS from the original one. Stabilization and consensus of the transformed agent states ensure both the satisfaction of the time-varying constraints and the consensus of the original agent states. Based on the Nussbaum gain …

Learning Meaningful Representations Of Surgical Motion Without Annotations, Robert Dipietro

Link Foundation Modeling, Simulation and Training Fellowship Reports

Superior technical skill in the operating room is associated with better patient outcomes [3,18], and at the core of surgical education is the belief that technical skill is improved through deliberate practice and appropriate feedback [10,17]. However, current standards for providing technical skills training are constrained by time [2], and most available methods for surgical skill assessment are subjective and global [14]. This has motivated interest in delivering targeted and automated assessment and feedback with machines, especially in robot-assisted surgery, during which high-quality surgical motion data can be captured transparently for analysis. Automated surgical activity recognition is an important precursor …

Directional Co-Clustering, Aghiles Salah, Mohamed Nadif

Research Collection School Of Computing and Information Systems

Co-clustering addresses the problem of simultaneous clustering of both dimensions of a data matrix. When dealing with high dimensional sparse data, co-clustering turns out to be more beneficial than one-sided clustering even if one is interested in clustering along one dimension only. Aside from being high dimensional and sparse, some datasets, such as document-term matrices, exhibit directional characteristics, and the L2 normalization of such data, so that it lies on the surface of a unit hypersphere, is useful. Popular co-clustering assumptions such as Gaussian or Multinomial are inadequate for this type of data. In this paper, we extend the scope …

Self-Refining Deep Symmetry Enhanced Network For Rain Removal, Hong Liu, Hanrong Ye, Xia Li, Wei Shi, Mengyuan Liu, Qianru Sun

Research Collection School Of Computing and Information Systems

Rain removal aims to remove the rain streaks on rain images. Traditional methods based on convolutional neural network (CNN) have achieved impressive results. However, these methods are under-performed when dealing with tilted rain streaks, because CNN is not equivariant to object rotations. To tackle this problem, we propose the Deep Symmetry Enhanced Network (DSEN) that explicitly extracts and learns from rotation-equivariant features from rain images. In addition, we design a self-refining strategy to remove rain streaks in a coarse-to-fine manner. The key idea is to reuse DSEN with an information link which passes the gradient flow to the finer stage. …

Efficient Distributed Reachability Querying Of Massive Temporal Graphs, Tianming Zhang, Yunjun Gao, Chen Lu, Wei Guo, Shiliang Pu, Baihua Zheng, Christian S. Jensen

Research Collection School Of Computing and Information Systems

Reachability computation is a fundamental graph functionality with a wide range of applications. In spite of this, little work has as yet been done on efficient reachability queries over temporal graphs, which are used extensively to model time-varying networks, such as communication networks, social networks, and transportation schedule networks. Moreover, we are faced with increasingly large real-world temporal networks that may be distributed across multiple data centers. This state of affairs motivates the paper's study of efficient reachability queries on distributed temporal graphs. We propose an efficient index, called Temporal Vertex Labeling (TVL), which is a labeling scheme for distributed …

Finding Flaws From Password Authentication Code In Android Apps, Siqi Ma, Elisa Bertino, Surya Nepal, Jianru Li, Ostry Diethelm, Robert H. Deng, Sanjay Jha

Research Collection School Of Computing and Information Systems

Password authentication is widely used to validate users’ identities because it is convenient to use, easy for users to remember, and simple to implement. The password authentication protocol transmits passwords in plaintext, which makes the authentication vulnerable to eavesdropping and replay attacks, and several protocols have been proposed to protect against this. However, we find that secure password authentication protocols are often implemented incorrectly in Android applications (apps). To detect the implementation flaws in password authentication code, we propose GLACIATE, a fully automated tool combining machine learning and program analysis. Instead of creating detection templates/rules manually, GLACIATE automatically and accurately …

Can Earables Support Effective User Engagement During Weight-Based Gym Exercises?, Meeralakshmi Radhakrishnan, Archan Misra

Research Collection School Of Computing and Information Systems

We explore the use of personal ‘earable’ devices (widely used by gym-goers) in providing personalized, quantified insights and feedback to users performing gym exercises. As in-ear sensing by itself is often too weak to pick up exercise-driven motion dynamics, we propose a novel, low-cost system that can monitor multiple concurrent users by fusing data from (a) wireless earphones, equipped with inertial and physiological sensors and (b) inertial sensors attached to exercise equipment. We share preliminary findings from a small-scale study to demonstrate the promise of this approach, as well as identify open challenges.

A Low-Cost Soft Robotic Hand Exoskeleton For Use In Therapy Of Limited Hand–Motor Function, Grant Rudd, Liam Daly, Vukica Jovanovic, Filip Cukov

Engineering Technology Faculty Publications

We present the design and validation of a low-cost, customizable and 3D-printed anthropomorphic soft robotic hand exoskeleton for rehabilitation of hand injuries using remotely administered physical therapy regimens. The design builds upon previous work done on cable actuated exoskeleton designs by implementing the same kinematic functionality, but with the focus shifted to ease of assembly and cost effectiveness as to allow patients and physicians to manufacture and assemble the hardware necessary to implement treatment. The exoskeleton was constructed solely from 3D-printed and widely available of-the-shelf components. Control of the actuators was realized using an Arduino microcontroller, with a custom-designed shield …

An Evolutionary Perspective On Foraging Strategies And Group Dynamics In Bio-Social Inspired Cognitive Radio Networks, Anna Wisniewska

Dissertations, Theses, and Capstone Projects

Saturation of wireless channels is inevitable as the number of wireless devices grows exponentially in an environment of limited radio spectrum capacity. Cognitive radio technology has been proposed to relieve overcrowded spectrum resources by allowing licensed channels to be opportunistically accessed by unlicensed users (cognitive radio devices) during periods of time when the license holder (primary user) is absent from its channel. Uncoordinated competition over limited resources among cognitive radio devices poses complex co-existence challenges. We propose novel bio-social inspired behavioral models and map out plausible evolutionary trajectories of co-use strategies in the cognitive radio ecosystem. By drawing parallels between …

Semi-Supervised Regression With Generative Adversarial Networks Using Minimal Labeled Data, Greg Olmschenk

Dissertations, Theses, and Capstone Projects

This work studies the generalization of semi-supervised generative adversarial networks (GANs) to regression tasks. A novel feature layer contrasting optimization function, in conjunction with a feature matching optimization, allows the adversarial network to learn from unannotated data and thereby reduce the number of labels required to train a predictive network. An analysis of simulated training conditions is performed to explore the capabilities and limitations of the method. In concert with the semi-supervised regression GANs, an improved label topology and upsampling technique for multi-target regression tasks are shown to reduce data requirements. Improvements are demonstrated on a wide variety of vision …

Do It Like A Syntactician: Using Binary Gramaticality Judgements To Train Sentence Encoders And Assess Their Sensitivity To Syntactic Structure, Pablo Gonzalez Martinez

Dissertations, Theses, and Capstone Projects

The binary nature of grammaticality judgments and their use to access the structure of syntax are a staple of modern linguistics. However, computational models of natural language rarely make use of grammaticality in their training or application. Furthermore, developments in modern neural NLP have produced a myriad of methods that push the baselines in many complex tasks, but those methods are typically not evaluated from a linguistic perspective. In this dissertation I use grammaticality judgements with artificially generated ungrammatical sentences to assess the performance of several neural encoders and propose them as a suitable training target to make models learn …

Be Sensitive And Collaborative: Analyzing Impact Of Coverage Metrics In Greybox Fuzzing, Jinghan Wang, Yue Duan, Wei Song, Heng Yin, Chengyu Song

Research Collection School Of Computing and Information Systems

Coverage-guided greybox fuzzing has become one of the most common techniques for finding software bugs. Coverage metric, which decides how a fuzzer selects new seeds, is an essential parameter of fuzzing and can significantly affect the results. While there are many existing works on the effectiveness of different coverage metrics on software testing, little is known about how different coverage metrics could actually affect the fuzzing results in practice. More importantly, it is unclear whether there exists one coverage metric that is superior to all the other metrics. In this paper, we report the first systematic study on the impact …

A Common Approach For Consumer And Provider Fairness In Recommendations, Dimitris Sacharidis, Kyriakos Mouratidis, Dimitrios Kleftogiannis

Research Collection School Of Computing and Information Systems

We present a common approach for handling consumer and provider fairness in recommendations. Our solution requires defining two key components, a classification of items and a target distribution, which together define the case of perfect fairness. This formulation allows distinct fairness concepts to be specified in a common framework. We further propose a novel reranking algorithm that optimizes for a desired trade-off between utility and fairness of a recommendation list.