OS and Networks Commons^™

Learning Semantically Rich Network-Based Multi-Modal Mobile User Interface Embeddings, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Semantically rich information from multiple modalities - text, code, images, categorical and numerical data - co-exist in the user interface (UI) design of mobile applications. Moreover, each UI design is composed of inter-linked UI entities which support different functions of an application, e.g., a UI screen comprising a UI taskbar, a menu and multiple button elements. Existing UI representation learning methods unfortunately are not designed to capture multi-modal and linkage structure between UI entities. To support effective search and recommendation applications over mobile UIs, we need UI representations that integrate latent semantics present in both multi-modal information and linkages between …

Topic-Guided Conversational Recommender In Multiple Domains, Lizi Liao, Ryuichi Takanobu, Yunshan Ma, Xun Yang, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational systems have recently attracted significant attention. Both the research community and industry believe that it will exert huge impact on human-computer interaction, and specifically, the IR/RecSys community has begun to explore Conversational Recommendation. In real-life scenarios, such systems are often urgently needed in helping users accomplishing different tasks under various situations. However, existing works still face several shortcomings: (1) Most efforts are largely confined in single task setting. They fall short of hands in handling tasks across domains. (2) Aside from soliciting user preference from dialogue history, a conversational recommender naturally has access to the back-end data structure which …

Malware And Memory Forensics On M1 Macs, Charles E. Glass

LSU Master's Theses

As malware continues to evolve, infection mechanisms that can only be seen in memory are increasingly commonplace. These techniques evade traditional forensic analysis, requiring the use of memory forensics. Memory forensics allows for the recovery of historical data created by running malware, including information that it tries to hide. Memory analysis capabilities have lagged behind on Apple's new M1 architecture while the number of malicious programs only grows. To make matters worse, Apple has developed Rosetta 2, the translation layer for running x86_64 binaries on an M1 Mac. As a result, all malware compiled for Intel Macs is theoretically functional …

Improving Memory Forensics Capabilities On Apple M1 Computers, Raphaela Santos Mettig Rocha

LSU Master's Theses

Malware threats are rapidly evolving to use more sophisticated attacks. By abusing rich application APIs such as Objective-C’s, they are able to gather information about user activity, launch background processes without the user’s knowledge as well as perform other malicious activities. In some cases, memory forensics is the only way to recover artifacts related to this malicious activity, as is the case with memory-only execution. The introduction of the Rosetta 2 on the Apple M1 introduces a completely new attack surface by allowing binaries of both Intel x86 64 and ARM64 architecture to run in userland. For this reason it …

Passing Time And Syncing Secrets: Demonstrating Covert Channel Vulnerabilities In Precision Time Protocol (Ptp), Aron J. Smith-Donovan

Mathematics, Statistics, and Computer Science Honors Projects

Covert channels use steganographic approaches to transfer secret digital communications; when applied to network protocols, these strategies can facilitate undetectable data exfiltration and insertion attacks. Because covert channel techniques are protocol- and implementation-specific, individual case studies are necessary to assess for vulnerabilities under different conditions. While several investigations have been published evaluating covert channel potential in infrastructure- and manufacturing-based contexts, no existing research explores Precision Time Protocol (PTP), a time synchronization protocol commonly used in industrial control systems. This study aims to fill this gap by demonstrating the feasibility of a covert channel-based attack on a PTP-enabled network.

On Size-Oriented Long-Tailed Graph Classification Of Graph Neural Networks, Zemin Liu, Qiheng Mao, Chenghao Liu, Yuan Fang, Jianling Sun

Research Collection School Of Computing and Information Systems

The prevalence of graph structures attracts a surge of investigation on graph data, enabling several downstream tasks such as multigraph classification. However, in the multi-graph setting, graphs usually follow a long-tailed distribution in terms of their sizes, i.e., the number of nodes. In particular, a large fraction of tail graphs usually have small sizes. Though recent graph neural networks (GNNs) can learn powerful graph-level representations, they treat the graphs uniformly and marginalize the tail graphs which suffer from the lack of distinguishable structures, resulting in inferior performance on tail graphs. To alleviate this concern, in this paper we propose a …

Pre-Training Graph Neural Networks For Link Prediction In Biomedical Networks, Yahui Long, Min Wu, Yong Liu, Yuan Fang, Chee Kong Kwoh, Jiawei Luo, Xiaoli Li

Research Collection School Of Computing and Information Systems

Motivation: Graphs or networks are widely utilized to model the interactions between different entities (e.g., proteins, drugs, etc) for biomedical applications. Predicting potential links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been designed for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g., sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks. Results: In …

Resil: Revivifying Function Signature Inference Using Deep Learning With Domain-Specific Knowledge, Yan Lin, Debin Gao, David Lo

Research Collection School Of Computing and Information Systems

Function signature recovery is important for binary analysis and security enhancement, such as bug finding and control-flow integrity enforcement. However, binary executables typically have crucial information vital for function signature recovery stripped off during compilation. To make things worse, recent studies show that many compiler optimization strategies further complicate the recovery of function signatures with intended violations to function calling conventions.In this paper, we first perform a systematic study to quantify the extent to which compiler optimizations (negatively) impact the accuracy of existing deep learning techniques for function signature recovery. Our experiments show that a state-of-the-art deep learning technique has …

Learning Scenario Representation For Solving Two-Stage Stochastic Integer Programs, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity. To solve two-stage SIPs efficiently, we propose a conditional variational autoencoder (CVAE) based method to learn scenario representation for a class of SIP instances. Specifically, we design a graph convolutional network based encoder to embed each scenario with the deterministic part of its instance (i.e. context) into a low-dimensional latent space, from which a decoder reconstructs the scenario from its latent representation conditioned on the context. Such a design effectively captures the dependencies of …

Chosen-Instruction Attack Against Commercial Code Virtualization Obfuscators, Shijia Li, Chunfu Jia, Pengda Qiu, Qiyuan Chen, Jiang Ming, Debin Gao

Research Collection School Of Computing and Information Systems

—Code virtualization is a well-known sophisticated obfuscation technique that uses custom virtual machines (VM) to emulate the semantics of original native instructions. Commercial VM-based obfuscators (e.g., Themida and VMProtect) are often abused by malware developers to conceal malicious behaviors. Since the internal mechanism of commercial obfuscators is a black box, it is a daunting challenge for the analyst to understand the behavior of virtualized programs. To figure out the code virtualization mechanism and design deobfuscation techniques, the analyst has to perform reverse-engineering on large-scale highly obfuscated programs. This knowledge learning process suffers from painful cost and imprecision. In this project, …

Intrusion Attacks On Automotive Can And Their Detection, Halley M. Paulson

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

The main highway of communication in a vehicle is the Controller Area Network, commonly known by the acronym CAN. Any vulnerability in this network could allow bad actors to block communication between vehicle subsystems, risking the safety of the vehicle’s occupants. With the ever growing list of vulnerabilities being exposed in the CAN, it is critical to address its safety. This paper looks at one of the known vulnerabilities in the data link layer of the CAN and an Intrusion Detection System that could detect attacks on this network. We detail a few processes of the CAN, arbitration and error …

Ad-Corre: Adaptive Correlation-Based Loss For Facial Expression Recognition In The Wild, Ali Pourramezan Fard, Mohammad H. Mahoor

Electrical and Computer Engineering: Faculty Scholarship

Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide …

Improving Adversarial Attacks Against Malconv, Justin Burr

Masters Theses & Doctoral Dissertations

This dissertation proposes several improvements to existing adversarial attacks against MalConv, a raw-byte malware classifier for Windows PE files. The included contributions greatly improve the success rates and performance of gradient-based file overlay attacks. All improvements are included in a new open-source attack utility called BitCamo.

Several new payload initialization strategies for use with gradient-based attacks are proposed and evaluated as potential replacements for the randomized initialization method used by current attacks. An algorithm for determining the optimal payload size is also proposed. The resulting improvements achieve a 100% evasion rate against eligible target executables using an average payload size …

Multi-Dimensional Security Integrity Analysis Of Broad Market Internet-Connected Cameras, Mark A. Stanislav

Masters Theses & Doctoral Dissertations

This study used a quantitative approach with a cross-sectional, descriptive analysis survey design to examine the adherence of 40 internet-connected cameras against three IoT security frameworks to determine their overall security posture. Relevant literature was reviewed showing that prior studies in a similar regard had limitations, such as a small sample population, singular market segment focus, and/or a lack of validation against formalized frameworks. This study resulted in a uniform and multi-dimensional set of findings with supporting evidence, leading to a mapping against selected IoT security frameworks that was then quantitatively analyzed for their relative adherence as individual cameras, across …

Wifitrace: Network-Based Contact Tracing For Infectious Diseases Using Passive Wifi Sensing, Amee Trivedi, Camellia Zakaria, Rajesh Krishna Balan, Ann Becker, George Corey, Prashant Shenoy

Research Collection School Of Computing and Information Systems

Contact tracing is a well-established and effective approach for the containment of the spread of infectious diseases. While Bluetooth-based contact tracing method using phones has become popular recently, these approaches suffer from the need for a critical mass adoption to be effective. In this paper, we present WiFiTrace, a network-centric approach for contact tracing that relies on passive WiFi sensing with no client-side involvement. Our approach exploits WiFi network logs gathered by enterprise networks for performance and security monitoring, and utilizes them for reconstructing device trajectories for contact tracing. Our approach is specifically designed to enhance the efficacy of traditional …

Leveraging Machine Learning For Detecting Iot-Based Interference In Operational Wifi Networks [Poster], Josh Pulse

Research in the Capitol

IoT (Internet of Things) devices have become increasingly popular in recent years. IoT includes many smart home devices such as an Amazon Echo, smart lightbulbs, and smart sensors. These devices often include different networking protocols than are used in most WiFi devices but are in the same wireless band, leading to the possibility of interference. With the rise in the number of IoT devices, it is important to understand how they impact the existing WiFi networks that many people deploy in their home or business. In this research project, wireless traffic data will be collected in an environment containing both …

The Effect Of Using The Gamification Strategy On Academic Achievement And Motivation Towards Learning Problem-Solving Skills In Computer And Information Technology Course Among Tenth Grade Female Students, Mazyunah Almutairi, Prof. Ahmad Almassaad

International Journal for Research in Education

Abstract

This study aimed to identify the effect of using the gamification strategy on academic achievement and motivation towards learning problem-solving skills in computer and information technology course. A quasi-experimental method was adopted. The study population included tenth-grade female students in Al-Badi’ah schools in Riyadh. The sample consisted of 54 students divided into two equal groups: control group and experimental group. The study tools comprised an achievement test and the motivation scale. The results showed that there were statistically significant differences between the two groups in the academic achievement test in favor of the experimental group, with a large effect …

Modeling Functional Similarity In Source Code With Graph-Based Siamese Networks, Nikita Mehrotra, Navdha Agarwal, Piyush Gupta, Saket Anand, David Lo, Rahul Purandare

Research Collection School Of Computing and Information Systems

Code clones are duplicate code fragments that share (nearly) similar syntax or semantics. Code clone detection plays an important role in software maintenance, code refactoring, and reuse. A substantial amount of research has been conducted in the past to detect clones. A majority of these approaches use lexical and syntactic information to detect clones. However, only a few of them target semantic clones. Recently, motivated by the success of deep learning models in other fields, including natural language processing and computer vision, researchers have attempted to adopt deep learning techniques to detect code clones. These approaches use lexical information (tokens) …

Security Strategy In Combating Online Extremist Ideologies In Uae, Khalid Al-Qasimi

Journal of Police and Legal Sciences

This study aims at identifying the role of security strategies; the foundations of correct belief and good upbringing in the face of extremist ideology in order to protect the intellectual security of society. The researcher adopted the descriptive analytical approach in order to describe and analyze the role of the security strategy, the foundations of the correct faith and good upbringing in spreading moderation and combating extremist ideology through electronic websites.

The study has arrived at a number of findings, the most important of which are: extremist ideology cannot be confronted by traditional methods, but must be combated through modern …

Timestamp Estimation From Outdoor Scenes, Tawfiq Salem, Jisoo Hwang, Rafael Padilha

Annual ADFSL Conference on Digital Forensics, Security and Law

The increasing availability of smartphones allowed people to easily capture and share images on the internet. These images are often associated with metadata, including the image capture time (timestamp) and the location where the image was captured (geolocation). The metadata associated with images provides valuable information to better understand scenes and events presented in these images. The timestamp can be manipulated intentionally to provide false information to convey a twisted version of reality. Images with manipulated timestamps are often used as a cover-up for wrongdoing or broadcasting false claims and competing views on the internet. Estimating the time of capture …

Anatomy Of An Internet Hijack And Interception Attack: A Global And Educational Perspective, Ben A. Scott, Michael N. Johnstone, Patryk Szewczyk

Annual ADFSL Conference on Digital Forensics, Security and Law

The Internet’s underlying vulnerable protocol infrastructure is a rich target for cyber crime, cyber espionage and cyber warfare operations. The stability and security of the Internet infrastructure are important to the function of global matters of state, critical infrastructure, global e-commerce and election systems. There are global approaches to tackle Internet security challenges that include governance, law, educational and technical perspectives. This paper reviews a number of approaches to these challenges, the increasingly surgical attacks that target the underlying vulnerable protocol infrastructure of the Internet, and the extant cyber security education curricula; we find the majority of predominant cyber security …

Automating App Review Response Generation Based On Contextual Knowledge, Cuiyun Gao, Wenjie Zhou, Xin Xia, David Lo, Qi Xie, Michael R. Lyu

Research Collection School Of Computing and Information Systems

User experience of mobile apps is an essential ingredient that can influence the user base and app revenue. To ensure good user experience and assist app development, several prior studies resort to analysis of app reviews, a type of repository that directly reflects user opinions about the apps. Accurately responding to the app reviews is one of the ways to relieve user concerns and thus improve user experience. However, the response quality of the existing method relies on the pre-extracted features from other tools, including manually labelled keywords and predicted review sentiment, which may hinder the generalizability and flexibility of …

Taming The Data In The Internet Of Vehicles, Shahab Tayeb

Mineta Transportation Institute

As an emerging field, the Internet of Vehicles (IoV) has a myriad of security vulnerabilities that must be addressed to protect system integrity. To stay ahead of novel attacks, cybersecurity professionals are developing new software and systems using machine learning techniques. Neural network architectures improve such systems, including Intrusion Detection System (IDSs), by implementing anomaly detection, which differentiates benign data packets from malicious ones. For an IDS to best predict anomalies, the model is trained on data that is typically pre-processed through normalization and feature selection/reduction. These pre-processing techniques play an important role in training a neural network to optimize …

Nft Sneaker Marketplace Design, Testing, And Challenges, Chris Zhu

Honors Theses

This paper introduces the preliminary background and implementation of the NFT sneaker marketplace. Specifically, we build sneaker NFTs on top of ERC-20 within the Ethereum network and use a top-to-bottom design mechanism. Our website performs well in its functionality, compatibility, and performance. We discuss possible future steps for security implementation. In particular, we recommend using a cold wallet for clients' transactions and implementing multi-signature contracts to avoid spoofing and repudiation. Introducing the sneaker NFT marketplace will vastly reduce the costs of transactions and delivery time in the physical sneaker marketplace. We hope investors in the physical asset space can find …

Detecting The Presence Of Electronic Devices In Smart Homes Using Harmonic Radar, Beatrice Perez, Gregory Mazzaro, Timothy J. Pierson, David Kotz

Dartmouth Scholarship

Data about users is collected constantly by phones, cameras, Internet websites, and others. The advent of so-called ‘Smart Things' now enable ever-more sensitive data to be collected inside that most private of spaces: the home. The first step in helping users regain control of their information (inside their home) is to alert them to the presence of potentially unwanted electronics. In this paper, we present a system that could help homeowners (or home dwellers) find electronic devices in their living space. Specifically, we demonstrate the use of harmonic radars (sometimes called nonlinear junction detectors), which have also been used in …

Smart Decision-Making Via Edge Intelligence For Smart Cities, Nathaniel Hudson

Theses and Dissertations--Computer Science

Smart cities are an ambitious vision for future urban environments. The ultimate aim of smart cities is to use modern technology to optimize city resources and operations while improving overall quality-of-life of its citizens. Realizing this ambitious vision will require embracing advancements in information communication technology, data analysis, and other technologies. Because smart cities naturally produce vast amounts of data, recent artificial intelligence (AI) techniques are of interest due to their ability to transform raw data into insightful knowledge to inform decisions (e.g., using live road traffic data to control traffic lights based on current traffic conditions). However, training and …

A Lightweight Reliably Quantified Deepfake Detection Approach, Tianyi Wang, Kam Pui Chow

Annual ADFSL Conference on Digital Forensics, Security and Law

Deepfake has brought huge threats to society such that everyone can become a potential victim. Current Deepfake detection approaches have unsatisfactory performance in either accuracy or efficiency. Meanwhile, most models are only evaluated on different benchmark test datasets with different accuracies, which could not imitate the real-life Deepfake unknown population. As Deepfake cases have already been raised and brought challenges at the court, it is disappointed that no existing work has studied the model reliability and attempted to make the detection model act as the evidence at the court. We propose a lightweight Deepfake detection deep learning approach using the …

Development Of A Framework To Support Informed Shipbuilding Based On Supply Chain Disruptions, Katherine Smith, Rafael Diaz, Yuzhong Shen

VMASC Publications

In addition to stresses induced by the Covid-19 pandemic, supply chains worldwide have been growing more complex while facing a continuous onslaught of disruptions. This paper presents an analysis and extension of a graph based model for modeling and simulating the effects of such disruptions. The graph based model combines a Bayesian network approach for simulating risks with a network dependency analysis approach for simulating the propagation of disruptions through the network over time. The initial analysis provides evidence supporting extension to for using a multi-layered approach allowing for the inclusion of cyclic features in supply chain models. Initial results …

A Low-Cost Machine Learning Based Network Intrusion Detection System With Data Privacy Preservation, Jyoti Fakirah, Lauhim Mahfuz Zishan, Roshni Mooruth, Michael L. Johnstone, Wencheng Yang

Annual ADFSL Conference on Digital Forensics, Security and Law

Network intrusion is a well-studied area of cyber security. Current machine learning-based network intrusion detection systems (NIDSs) monitor network data and the patterns within those data but at the cost of presenting significant issues in terms of privacy violations which may threaten end-user privacy. Therefore, to mitigate risk and preserve a balance between security and privacy, it is imperative to protect user privacy with respect to intrusion data. Moreover, cost is a driver of a machine learning-based NIDS because such systems are increasingly being deployed on resource-limited edge devices. To solve these issues, in this paper we propose a NIDS …

Human-Controlled Fuzzing With Afl, Maxim Grishin, Igor Korkin, Phd

Annual ADFSL Conference on Digital Forensics, Security and Law

Fuzzing techniques are applied to reveal different types of bugs and vulnerabilities. American Fuzzy Lop (AFL) is a free most popular software fuzzer used by many other fuzzing frameworks. AFL supports autonomous mode of operation that uses the previous step output into the next step, as a result fuzzer spends a lot of time analyzing minor code sections. By making fuzzing process more focused and human controlled security expert can save time and find more bugs in less time. We designed a new module that can fuzz only the specified functions. As a result, the chosen ones will be inspected …