Physical Sciences and Mathematics Commons^™

Towards A Robust Defense: A Multifaceted Approach To The Detection And Mitigation Of Neural Backdoor Attacks Through Feature Space Exploration And Analysis, Liuwan Zhu

Electrical & Computer Engineering Theses & Dissertations

From voice assistants to self-driving vehicles, machine learning(ML), especially deep learning, revolutionizes the way we work and live, through the wide adoption in a broad range of applications. Unfortunately, this widespread use makes deep learning-based systems a desirable target for cyberattacks, such as generating adversarial examples to fool a deep learning system to make wrong decisions. In particular, many recent studies have revealed that attackers can corrupt the training of a deep learning model, e.g., through data poisoning, or distribute a deep learning model they created with “backdoors” planted, e.g., distributed as part of a software library, so that the …

Multi-Granularity Detector For Vulnerability Fixes, Truong Giang Nguyen, Cong, Thanh Le, Hong Jin Kang, Ratnadira Widyasari, Chengran Yang, Zhipeng Zhao, Bowen Xu, Jiayuan Zhou, Xin Xia, Ahmed E. Hassan, David Lo, David Lo

Research Collection School Of Computing and Information Systems

With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert users of such vulnerabilities. SCA requires the identification of vulnerability-fixing commits. Prior works have proposed methods that can automatically identify such vulnerability-fixing commits. However, identifying such commits is highly challenging, as only a very small minority of commits are vulnerability fixing. Moreover, code changes can be noisy and difficult to analyze. We observe that noise can occur at different levels of detail, making it challenging to detect vulnerability fixes accurately. To address these challenges and …

Mastering Stock Markets With Efficient Mixture Of Diversified Trading Experts, Shuo Sun, Xinrun Wang, Wanqi Xue, Xiaoxuan Lou, Bo An

Research Collection School Of Computing and Information Systems

Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, the performance of existing DL methods is unstable with sensitivity to network initialization and hyperparameter selection. One major limitation of existing works is that investment decisions are made based on one individual neural network predictor with high uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle this limitation, we propose AlphaMix, a novel three-stage …

Characterization And Estimation Of Musculoskeletal Pain Using Machine Learning, Boluwatife Faremi

Master's Theses

Traditional scales utilized for recording pain are known to be highly subjective and biased due to inaccuracies in recollecting actual pain intensities. As a result, machine learning (ML) models that are trained using these scores as ground truth are reported to have low performance for objective pain classification because of the huge disparity between what was felt in moments of pain and the scores recorded afterward.

In the present study, two devices were designed for gathering real-time, continuous in-session subjective pain scores and the recording of the autonomic nervous system (ANS) altered endodermal (EDA) activity. 24 participants were recruited to …

Artificial Intelligence Frameworks To Detect And Investigate The Pathophysiology Of Spaceflight Associated Neuro-Ocular Syndrome (Sans), Joshua Ong, Ethan Waisberg, Mouayad Masalkhi, Sharif Amit Kamran, Kemper Lowry, Prithul Sarker, Nasif Zaman, Phani Paladugu, Alireza Tavakkoli, Andrew G Lee

Student Papers, Posters & Projects

Spaceflight associated neuro-ocular syndrome (SANS) is a unique phenomenon that has been observed in astronauts who have undergone long-duration spaceflight (LDSF). The syndrome is characterized by distinct imaging and clinical findings including optic disc edema, hyperopic refractive shift, posterior globe flattening, and choroidal folds. SANS serves a large barrier to planetary spaceflight such as a mission to Mars and has been noted by the National Aeronautics and Space Administration (NASA) as a high risk based on its likelihood to occur and its severity to human health and mission performance. While it is a large barrier to future spaceflight, the underlying …

Understanding Political Polarization Using Language Models: A Dataset And Method, Samiran Gode, Supreeth Bare, Bhiksha Raj, Hyungon Yoo

Natural Language Processing Faculty Publications

Our paper aims to analyze political polarization in US political system using language models, and thereby help candidates make an informed decision. The availability of this information will help voters understand their candidates' views on the economy, healthcare, education, and other social issues. Our main contributions are a dataset extracted from Wikipedia that spans the past 120 years and a language model-based method that helps analyze how polarized a candidate is. Our data are divided into two parts, background information and political information about a candidate, since our hypothesis is that the political views of a candidate should be based …

Prompt-Based Tuning Of Transformer Models For Multi-Center Medical Image Segmentation Of Head And Neck Cancer, Numan Saeed, Muhammad Ridzuan, Roba Al Majzoub, Mohammad Yaqub

Computer Vision Faculty Publications

Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this task. However, to build a powerful backbone, the self-attention block of ViT requires large-scale pre-training data. The present method of modifying pre-trained models entails updating all or some of the backbone parameters. This paper proposes a novel fine-tuning strategy for adapting a pretrained transformer-based segmentation model on data from a new medical center. This method introduces a small number of learnable parameters, termed prompts, into the input space (less than …

On Training Neurons With Bounded Compilations, Lance Kennedy

Master of Science in Computer Science Theses

Knowledge compilation offers a formal approach to explaining and verifying the behavior of machine learning systems, such as neural networks. Unfortunately, compiling even an individual neuron into a tractable representation such as an Ordered Binary Decision Diagram (OBDD), is an NP-hard problem. In this thesis, we consider the problem of training a neuron from data, subject to the constraint that it has a compact representation as an OBDD. Our approach is based on the observation that a neuron can be compiled into an OBDD in polytime if (1) the neuron has integer weights, and (2) its aggregate weight is bounded. …

International Soft Law Governance Of Artificial Intelligence Ethics: Current Situation, Challenges And Countermeasures, Mingting Zhu, Chongli Xu

Bulletin of Chinese Academy of Sciences (Chinese Version)

Artificial intelligence (AI) technology not only rapidly empowers economic and social development, but may also trigger many ethical issues highly related to the characteristics and development of AI technology itself. The rise of international soft law in the field of AI ethical governance is almost inevitable due to its flexibility, efficiency, low application cost, ability to fill the gap in hard law, and convenience in distinguishing governance and layered response to ethical issues. Under the current situation of developed international soft law and outdated hard law in this field, faced with the governance challenge of unstable cooperation among subjects of …

How Technology May Be Used For Future Disease Predictions, Rich P. Manprisio

Journal of Applied Disciplines

Exasperated by the ongoing global pandemic, the healthcare system is grappling with the formidable challenges posed by proper and effective disease treatments. Nevertheless, amidst these growing difficulties, the healthcare field has witnessed significant technological advancements, offering promising avenues for disease prediction. Notably, a positive correlation exists between the utilization of technologies and their potential to serve as valuable tools for disease prediction. As our reliance on technological sophistication continues progressing, current research highlights numerous viable options to augment the healthcare sector. This review explores the current state of utilizing technologies and their potential to enhance healthcare, shedding light on their …

Using Machine Learning Techniques To Model Encoder/Decoder Pair For Non-Invasive Electroencephalographic Wireless Signal Transmission, Ernst Fanfan

Master of Science in Computer Science Theses

This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating …

Enhancing Video-Based Learning Using Knowledge Tracing: Personalizing Students’ Learning Experience With Orbits, Shady Shehata, David Santandreu, Philip Purnell, Mark Thompson

Natural Language Processing Faculty Publications

As the world regains its footing following the COVID-19 pandemic, academia is striving to consolidate the gains made in students’ education experience. New technologies such as video-based learning have shown some early improvement in student learning and engagement. In this paper, we present ORBITS predictive engine at YOURIKA company, a video-based student support platform powered by knowledge tracing. In an exploratory case study of one master’s level Speech Processing course at the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi, half the students used the system while the other half did not. Student qualitative feedback was universally …

Ways To Participate In Ongoing Regulation Around Artificial Intelligence Ethics In The United States, Wilhelmina Randtke

Library Faculty Presentations

In January 2021, the US passed the National Artificial Intelligence Initiative Act of 2020. The goal is a cohesive federal AI initiative, and part of that is safety, ethics, and transparency. The act includes funding appropriations for 2021-2025, and roll out takes place over that time. In implementing this law, there is recent and ongoing activity to regulate AI in the US. Regular calls for public participation go out to the public on www.federalregister.gov in the form of open ended questions on which input is requested, and feedback on reports or action plans.

The linked data community is uniquely positioned …

On Teaching Multi-Criteria Decision Making With A Robot Assistant, Chen Zhang, Hakan Saraoglu, David A. Louton

Information Systems and Analytics Department Faculty Conference Proceedings

We propose a system and method for a robot assistant for teaching multi-attribute decision making (MCDM). Through questions and answers in natural language, the robot assistant learns the user’s preferences on multiple criteria involving a selection decision and makes recommendations using data on each criterion and the learned user preferences. It will include a use-case demonstration where NAO the robot will assist a human in forming a simple portfolio of mutual funds. Presenters will illustrate the architecture of the robot assisted MCDM and describe a method that is extensively used to structure complex decision problems and has been applied to …

Towards Enabling Haptic Communications Over 6g: Issues And Challenges, Muhammad Awais, Fasih Ullah Khan, Muhammad Zafar, Muhammad Mudassar, Muhammad Zaigham Zaheer, Khalid Mehmood Cheema, Muhammad Kamran, Woo Sung Jung

Computer Vision Faculty Publications

This research paper provides a comprehensive overview of the challenges and potential solutions related to enabling haptic communication over the Tactile Internet in the context of 6G networks. The increasing demand for multimedia services and device proliferation has resulted in limited radio resources, posing challenges in their efficient allocation for Device-to-Device (D2D)-assisted haptic communications. Achieving ultra-low latency, security, and energy efficiency are crucial requirements for enabling haptic communication over TI. The paper explores various methodologies, technologies, and frameworks that can facilitate haptic communication, including backscatter communications (BsC), non-orthogonal multiple access (NOMA), and software-defined networks. Additionally, it discusses the potential of …

Case Study: The Impact Of Emerging Technologies On Cybersecurity Education And Workforces, Austin Cusak

Journal of Cybersecurity Education, Research and Practice

A qualitative case study focused on understanding what steps are needed to prepare the cybersecurity workforces of 2026-2028 to work with and against emerging technologies such as Artificial Intelligence and Machine Learning. Conducted through a workshop held in two parts at a cybersecurity education conference, findings came both from a semi-structured interview with a panel of experts as well as small workgroups of professionals answering seven scenario-based questions. Data was thematically analyzed, with major findings emerging about the need to refocus cybersecurity STEM at the middle school level with problem-based learning, the disconnects between workforce operations and cybersecurity operators, the …

Face Readers: The Frontier Of Computer Vision And Math Learning, Beverly Woolf, Margrit Betke, Hao Yu, Sarah Adel Bargal, Ivan Arroyo, John J. Magee Iv, Danielle Allessio, William Rebelsky

Computer Science

The future of AI-assisted individualized learning includes computer vision to inform intelligent tutors and teachers about student affect, motivation and performance. Facial expression recognition is essential in recognizing subtle differences when students ask for hints or fail to solve problems. Facial features and classification labels enable intelligent tutors to predict students’ performance and recommend activities. Videos can capture students’ faces and model their effort and progress; machine learning classifiers can support intelligent tutors to provide interventions. One goal of this research is to support deep dives by teachers to identify students’ individual needs through facial expression and to provide immediate …

Linear Classifier: An Often-Forgotten Baseline For Text Classification, Yu Chen Lin, Si An Chen, Jie Jyun Liu, Chih Jen Lin

Machine Learning Faculty Publications

Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the obtained model. In this opinion paper, we point out that this way may only sometimes get satisfactory results. We argue the importance of running a simple baseline like linear classifiers on bag-of-words features along with advanced methods. First, for many text data, linear methods show competitive performance, high efficiency, and robustness. Second, advanced models such as BERT may only achieve the best results if properly …

Team Thesyllogist At Semeval-2023 Task 3: Language-Agnostic Framing Detection In Multi-Lingual Online News: A Zero-Shot Transfer Approach, Osama Mohammed Afzal, Preslav Nakov

Natural Language Processing Faculty Publications

We describe our system for SemEval-2022 Task 3 subtask 2 which on detecting the frames used in a news article in a multi-lingual setup. We propose a multi-lingual approach based on machine translation of the input, followed by an English prediction model. Our system demonstrated good zero-shot transfer capability, achieving micro-F1 scores of 53% for Greek (4th on the leaderboard) and 56.1% for Georgian (3rd on the leaderboard), without any prior training on translated data for these languages. Moreover, our system achieved comparable performance on seven other languages, including German, English, French, Russian, Italian, Polish, and Spanish. Our results demonstrate …

Semeval-2023 Task 3: Detecting The Category, The Framing, And The Persuasion Techniques In Online News In A Multi-Lingual Setup, Jakub Piskorski, Nicolas Stefanovitch, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

We describe SemEval-2023 task 3 on Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multilingual Setup: the dataset, the task organization process, the evaluation setup, the results, and the participating systems. The task focused on news articles in nine languages (six known to the participants upfront: English, French, German, Italian, Polish, and Russian), and three additional ones revealed to the participants at the testing phase: Spanish, Greek, and Georgian). The task featured three subtasks: (1) determining the genre of the article (opinion, reporting, or satire), (2) identifying one or more frames used in an …

Multilingual Multifaceted Understanding Of Online News In Terms Of Genre, Framing And Persuasion Techniques, Jakub Piskorski, Nicolas Stefanovitch, Nikolaos Nikolaidis, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

We present a new multilingual multifacet dataset of news articles, each annotated for genre (objective news reporting vs. opinion vs. satire), framing (what key aspects are highlighted), and persuasion techniques (logical fallacies, emotional appeals, ad hominem attacks, etc.). The persuasion techniques are annotated at the span level, using a taxonomy of 23 fine-grained techniques grouped into 6 coarse categories. The dataset contains 1,612 news articles covering recent news on current topics of public interest in six European languages (English, French, German, Italian, Polish, and Russian), with more than 37k annotated spans of persuasion techniques. We describe the dataset and the …

Managing The Creative Frontier Of Generative Ai: The Novelty-Usefulness Tradeoff, Anirban. Mukherjee, Hannah H. Chang

Research Collection Lee Kong Chian School Of Business

In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead to limitations such as hallucinations and memorization. Hallucinations, characterized by AI responses containing random inaccuracies or falsehoods, emerge when models prioritize novelty over usefulness. Memorization, where AI models reproduce content from their training data, results from an excessive focus on usefulness, potentially limiting creativity. To address these challenges, we propose a framework that includes domain-specific analysis, data and transfer learning, user preferences and customization, custom evaluation metrics, …

Analysis Of Predictive Performance And Reliability Of Classifiers For Quality Assessment Of Medical Evidence Revealed Important Variation By Medical Area, Simon Šuster, Timothy Baldwin, Karin Verspoor

Natural Language Processing Faculty Publications

Objectives: A major obstacle in deployment of models for automated quality assessment is their reliability. To analyze their calibration and selective classification performance. Study Design and Setting: We examine two systems for assessing the quality of medical evidence, EvidenceGRADEr and RobotReviewer, both developed from Cochrane Database of Systematic Reviews (CDSR) to measure strength of bodies of evidence and risk of bias (RoB) of individual studies, respectively. We report their calibration error and Brier scores, present their reliability diagrams, and analyze the risk–coverage trade-off in selective classification. Results: The models are reasonably well calibrated on most quality criteria (expected calibration error …

Target-Based Offensive Language Identification, Marcos Zampieri, Skye Morgan, Kai North, Tharindu Ranasinghe, Austin Simmons, Paridhi Khandelwal, Sara Rosenthal, Preslav Nakov

Natural Language Processing Faculty Publications

We present TBO, a new dataset for Target-based Offensive language identification. TBO contains post-level annotations regarding the harmfulness of an offensive post and token-level annotations comprising of the target and the offensive argument expression. Popular offensive language identification datasets for social media focus on annotation taxonomies only at the post level and more recently, some datasets have been released that feature only token-level annotations. TBO is an important resource that bridges the gap between post-level and token-level annotation datasets by introducing a single comprehensive unified annotation taxonomy. We use the TBO taxonomy to annotate post-level and token-level offensive language on …

Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov

Natural Language Processing Faculty Publications

The naïve approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilingual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human …

Singapore's Hospital To Home Program: Raising Patient Engagement Through Ai, John Abisheganaden, Kheng Hock Lee, Lian Leng Low, Eugene Shum, Han Leong Goh, Christine Gian Lee Ang, Andy Wee An Ta, Steven M. Miller

Research Collection School Of Computing and Information Systems

Because of their complex care needs, many elderly patients are discharged from hospitals only to be readmitted for multiple stays within the following twelve months. John Abisheganaden and his fellow authors describe Singapore’s Hospital to Home program, a community care initiative fueled by artificial intelligence.

Singapore's Ai Applications In The Public Sector: Six Examples, Steven M. Miller

Research Collection School Of Computing and Information Systems

Steven M. Miller describes six instances in which Singapore has applied AI in the public sector, illustrating different ways of improving its engagement with the public by making government services more accessible, anywhere, anytime, and speeding its responses to public processes and feedback. He illustrates how its leaders made the city a living lab for AI use, and what they learned.

A Hierarchical Optimization Approach For Dynamic Pickup And Delivery Problem With Lifo Constraints, Jianhui Du, Zhiqin Zhang, Xu Wang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider a dynamic pickup and delivery problem (DPDP) where loading and unloading operations must follow a last in first out (LIFO) sequence. A fleet of vehicles will pick up orders in pickup points and deliver them to destinations. The objective is to minimize the total over-time (that is the amount of time that exceeds the committed delivery time) and total travel distance. Given the dynamics of orders and vehicles, this paper proposes a hierarchical optimization approach based on multiple intuitive yet often-neglected strategies, namely what we term as the urgent strategy, hitchhike strategy and packing-bags strategy. These multiple strategies …

Recognizing Hand Gestures Using Solar Cells, Dong Ma, Guohao Lan, Mahbub Hassan, Wen Hu, B. Mushfika Upama, Ashraf Uddin, Youseef, Moustafa

Research Collection School Of Computing and Information Systems

We design a system, SolarGest, which can recognize hand gestures near a solar-powered device by analyzing the patterns of the photocurrent. SolarGest is based on the observation that each gesture interferes with incident light rays on the solar panel in a unique way, leaving its discernible signature in harvested photocurrent. Using solar energy harvesting laws, we develop a model to optimize design and usage of SolarGest. To further improve the robustness of SolarGest under non-deterministic operating conditions, we combine dynamic time warping with Z-score transformation in a signal processing pipeline to pre-process each gesture waveform before it is analyzed for …

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a …