Computer Sciences Commons^™

Repairing Adversarial Texts Through Perturbation, Guoliang Dong, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay, Xinyu Wang, Ting Dai, Jie Shi, Jin Song Dong

Research Collection School Of Computing and Information Systems

It is known that neural networks are subject to attacks through adversarial perturbations. Worse yet, such attacks are impossible to eliminate, i.e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training. Multiple approaches have been developed to detect and reject such adversarial inputs. Rejecting suspicious inputs however may not be always feasible or ideal. First, normal inputs may be rejected due to false alarms generated by the detection algorithm. Second, denial-of-service attacks may be conducted by feeding such systems with adversarial inputs. To address this, in this work, we focus on the text domain and …

Leakage-Resilient Easily Deployable And Efficiently Searchable Encryption (Edese), Jiaming Yuan, Yingjiu Li, Jun Li, Daoyuan Wu, Jianting Ning, Yangguang Tian, Robert H. Deng

Research Collection School Of Computing and Information Systems

Easily Deployable and Efficiently Searchable Encryption (EDESE) is a cryptographic primitive designed for practical searchable applications, offering efficient search and easy deployment. However, it remains vulnerable to Leakage-Abuse attacks, allowing adversaries to exploit keyword-matching processes to extract sensitive information. To address these vulnerabilities, we introduce Leakage-Resilient EDESE (LR-EDESE) with k-indistinguishability and controlled leakage functions. We then propose Volume Leakage-Resilient EDESE (VLR-EDESE), a new scheme to protect against both query and document volume leakage. Our experimental results demonstrate that at k = 5000 (maximum security setting), VLR-EDESE incurs an overhead of 63× compared to the baseline EDESE without leakage protection, outperforming …

Runtime Anomaly Detection For Drones: An Integrated Rule-Mining And Unsupervised Learning Approach, Ivan Wei Han Tan, Wei Minn, Christopher M. Poskitt, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, have witnessed a remarkable surge in popularity due to their versatile applications. These cyber-physical systems depend on multiple sensor inputs, such as cameras, GPS receivers, accelerometers, and gyroscopes, with faults potentially leading to physical instability and serious safety concerns. To mitigate such risks, anomaly detection has emerged as a crucial safeguarding mechanism, capable of identifying the physical manifestations of emerging issues and allowing operators to take preemptive action at runtime. Recent anomaly detection methods based on LSTM neural networks have shown promising results, but three challenges persist: the need for models …

Milpbench: A Large-Scale Benchmark Test Suite For Mixed Integer Linear Programming Problems, Huigen Ye, Yaoyang Cheng, Hua Xu, Zhiguang Cao, Hanzhang Qin

Research Collection School Of Computing and Information Systems

Mixed-integer linear programming (MILP) is a cornerstone of optimization with applications across numerous domains. However, the development and evaluation of MILP-solving algorithms are hindered by existing benchmark datasets, which are often limited in scale, lack diversity, and are poorly structured, making them inadequate for systematic testing across different solving approaches, especially for machine learning (ML)-based methods. To address these issues, we introduce MILPBench, a large-scale benchmark suite comprising 100,000 MILP instances organized into 60 well-categorized classes. Using structural properties and embedding similarity metrics, we developed a novel classification framework to ensure both intra-class homogeneity and inter-class diversity. In addition to …

Collaboration With Dynamic Open Ad Hoc Team Via Team State Modelling, Jing Sun, Cong Zhang, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Open ad hoc teamwork presents the challenging problem of designing an autonomous agent that can rapidly adapt to collaborate with teammates without prior coordination in an open environment. Existing methods primarily rely on fixed, predefined teammate types, overlooking the fact that teammates may change dynamically. To address this limitation, we propose a novel reinforcement learning approach, the Open Online Teammate Adaptation Framework (Open-OTAF), which enables a controlled agent to collaborate with dynamic teammates in open ad hoc environments. To achieve this, the controlled agent employs a dual teamwork situation inference model to capture the current teamwork state, facilitating decision-making under …

Meta-Black-Box-Optimization Through Offline Q-Function Learning, Zeyuan Ma, Zhiguang Cao, Zhou Jiang, Hongshu Guo, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Recent progress in Meta-Black-Box-Optimization (MetaBBO) has demonstrated that using RL to learn a meta-level policy for dynamic algorithm configuration (DAC) over an optimization task distribution could significantly enhance the performance of the low-level BBO algorithm. However, the online learning paradigms in existing works makes the efficiency of MetaBBO problematic. To address this, we propose an offline learning-based MetaBBO framework in this paper, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO. Specifically, we first transform DAC task into long-sequence decision process. This allows us further introduce an effective Q-function decomposition mechanism to reduce the learning difficulty within the intricate …

Breaking The Reasoning Barrier: A Survey On Llm Complex Reasoning Through The Lens Of Self-Evolution, Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolution, and self-evolution. Data evolution explores methods to generate higher-quality reasoning training data. Model evolution focuses on training strategies to boost reasoning capabilities. Self-evolution research autonomous system evolution via iterating cycles of data and model evolution. We further discuss the scaling law of self-evolution and analyze representative O1-like works through this lens. By summarizing advanced methods and outlining future directions, this …

Finir: The 2nd Workshop On Financial Information Retrieval In The Era Of Generative Ai, Fengbin Zhu, Yunshan Ma, Fuli Feng, Chao Wang, Huanbo Luan, Guangnan Ye, Shuo Zhang, Dhagash Mehta, Pingping Chen, Bing Xiang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Recent advancements in Generative AI, such as Large Language Models (LLMs), have demonstrated remarkable success across various general tasks. Extensive studies have explored leveraging generative models in finance, but significant challenges persist. This half-day workshop explores potential approaches and research directions to address these challenges by equipping generative models with advanced Information Retrieval (IR) models. Specifically, this workshop seeks to provide a platform for discussing innovative ideas that facilitate the advancement of IR technology to enrich generative models in finance from four key perspectives: (i) financial IR techniques (ii) financial IR benchmarking and evaluation (iii) financial systems and agents/assistants (iv) …

Mitigating Regression Faults Induced By Feature Evolution In Deep Learning Systems, Hanmo Yu, Zan Wang, Xuyang Chen, Junjie Chen, Jun Sun, Shuang Liu, Zishuo Dong

Research Collection School Of Computing and Information Systems

Deep learning (DL) systems have been widely utilized across various domains. However, the evolution of DL systems can result in regression faults. In addition to the evolution of DL systems through the incorporation of new data, feature evolution, such as the addition of new features, is also common and can introduce regression faults. In this work, we first investigate the underlying factors that are correlated with regression faults in feature evolution scenarios, i.e., redundancy and contribution shift. Based on our investigation, we propose a novel mitigation approach called FeaProtect, which aims to minimize the impact of these two factors. To …

Crow: Eliminating Backdoors From Large Language Models Via Internal Consistency Regularization, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods—designed for vision/text classification tasks—fail for text generation. We propose Internal Consistency Regularization (CROW), a defense leveraging the observation that backdoored models exhibit unstable layer-wise hidden representations when triggered, while clean models show smooth transitions. CROW enforces consistency across layers via adversarial perturbations and regularization during finetuning, neutralizing backdoors without requiring clean reference models or trigger knowledge—only a small clean dataset. Experiments across Llama-2 (7B, 13B), CodeLlama (7B, 13B), and Mistral-7B demonstrate CROW’s effectiveness: it achieves significant reductions in attack success rates across …

Shield: Multi-Task Multi-Distribution Vehicle Routing Solver With Sparsity And Hierarchy, Yong Liang Goh, Zhiguang Cao, Yining Ma, Jianan Zhou, Mohammed Haroon Dupty, Wee Sun Lee

Research Collection School Of Computing and Information Systems

Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both sparsity and hierarchy principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficiency and generalization by allowing the model to dynamically select nodes to use or skip each decoder layer, …

Ts-Diff: Two-Stage Diffusion Model For Low-Light Raw Image Enhancement, Yi Li, Zhiyuan Zhang, Jiangnan Xia, Jianghan Cheng, Qilong Wu, Junwei Li

Research Collection School Of Computing and Information Systems

This paper presents a novel Two-Stage Diffusion Model (TS-Diff) for enhancing extremely low-light RAW images. In the pre-training stage, TS-Diff synthesizes noisy images by constructing multiple virtual cameras based on a noise space. Camera Feature Integration (CFI) modules are then designed to enable the model to learn generalizable features across diverse virtual cameras. During the aligning stage, CFIs are averaged to create a target-specific CFIT, which is fine-tuned using a small amount of real RAW data to adapt to the noise characteristics of specific cameras. A structural reparameterization technique further simplifies CFIT for efficient deployment. To address color shifts during …

Simulating Before Planning: Constructing Intrinsic User World Model For User-Tailored Dialogue Policy Planning, Tao He, Lizi Liao, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in dialogue policy planning have focused on optimizing system agent policies to achieve predefined goals, emphasizing strategy design, trajectory acquisition, and training efficiency. However, these approaches often overlook the critical role of user characteristics, which are essential in real-world scenarios like conversational search and recommendation, where interactions must adapt to individual user traits such as personality, preferences, and goals. To address this gap, we conduct a comprehensive study using task-specific user personas to evaluate dialogue policy planning under diverse user behaviors. Our analysis, based on these user profiles, reveals significant shortcomings in existing approaches, underscoring the necessity for …

Generalization Analysis For Supervised Contrastive Representation Learning Under Non‑Iid Settings, Minh Hieu Nong, Antoine Ledent

Research Collection School Of Computing and Information Systems

Contrastive Representation Learning (CRL) has achieved impressive success in various domains in recent years. Nevertheless, the theoretical understanding of the generalization behavior of CRL has remained limited. Moreover, to the best of our knowledge, the current literature only analyzes generalization bounds under the assumption that the data tuples used for contrastive learning are independently and identically distributed. However, in practice, we are often limited to a fixed pool of reusable labeled data points, making it inevitable to recycle data across tuples to create sufficiently large datasets. Therefore, the tuple-wise independence condition imposed by previous works is invalidated. In this paper, …

Grokformer: Graph Fourier Kolmogorov‑Arnold Transformers, Guoguo Ai, Guansong Pang, Hezhe Qiao, Yuan Gao, Hui Yan

Research Collection School Of Computing and Information Systems

Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self-attention, the core module of GTs, preserves only low-frequency signals in graph features, leading to ineffectiveness in capturing other important signals like high-frequency ones. Some recent GT models help alleviate this issue, but their flexibility and expressiveness are still limited since the filters they learn are fixed on predefined graph spectrum or spectral order. To tackle this challenge, we propose a Graph Fourier Kolmogorov-Arnold Transformer (GrokFormer), a novel GT model that learns highly expressive spectral filters with adaptive graph spectrum and spectral …

Cracking Aegis: An Adversarial Llm-Based Game For Raising Awareness Of Vulnerabilities In Privacy Protection, Jiaying Fu, Yiyang Lu, Zehua Yang, Fiona Fui-Hoon Nah, Ray Lc

Research Collection School Of Computing and Information Systems

Traditional methods for raising awareness of privacy protection often fail to engage users or provide hands-on insights into how privacy vulnerabilities are exploited. To address this, we incorporate an adversarial mechanic in the design of the dialogue-based serious game Cracking Aegis. Leveraging LLMs to simulate natural interactions, the game challenges players to impersonate characters and extract sensitive information from an AI agent, Aegis. A user study (n=22) revealed that players employed diverse deceptive linguistic strategies, including storytelling and emotional rapport, to manipulate Aegis. After playing, players reported connecting in-game scenarios with real-world privacy vulnerabilities, such as phishing and impersonation, and …

Exploring The Capabilities Of Llms For Code-Change-Related Tasks, Lishui Fan, Jiakun Liu, Zhongxin Liu, David Lo, Xin Xia, Shanping Li

Research Collection School Of Computing and Information Systems

Developers deal with code-change-related tasks daily, e.g., reviewing code. Pre-trained code and code-change-oriented models have been adapted to help developers with such tasks. Recently, large language models (LLMs) have shown their effectiveness in code-related tasks. However, existing LLMs for code focus on general code syntax and semantics rather than the differences between two code versions. Thus, it is an open question how LLMs perform on code-change-related tasks.To answer this question, we conduct an empirical study using 1B parameters LLMs on three code-change-related tasks, i.e., code review generation, commit message generation, and just-in-time comment update, with in-context learning (ICL) and parameter-efficient …

A Neuro-Symbolic Ai Approach To Scene Understanding In Autonomous Systems, Ruwan Tharanga Wickramarachchige Don

Theses and Dissertations

Effectively understanding scenes requires a unified representation of scene data and background knowledge. A neuro-symbolic AI approach to scene understanding leverages such a unified representation to enable advanced expression, inference, and labeling of scenes, improving the perception of autonomous systems.

Scene understanding remains a central challenge in the machine perception of autonomous systems. It requires the integration of multiple sources of information, background knowledge, and heterogeneous sensor data to perceive, interpret, and reason about both physical and semantic aspects of dynamic environments. Current approaches to scene understanding primarily rely on computer vision and deep learning models that operate directly on …

A Comparative Study Of Machine Learning And Deep Learning Models In Binary And Multiclass Classification For Intrusion Detection Systems, Ayesha Alharthi, Meera Alaryani, Sanaa Kaddoura

All Works

Network infrastructure evolution has significantly expanded the attack surface, leading to increasingly complex and sophisticated cybersecurity threats. Traditional rule-based intrusion detection systems (IDS) often fail to detect emerging attack vectors, prompting the need for intelligent, data-driven approaches. This study evaluates and compares the performance of machine learning (ML) and deep learning (DL) models for network intrusion detection. Two publicly available datasets were utilized: a binary-labeled software-defined networking (SDN) dataset and a multiclass industrial control system dataset based on the IEC 60870-5-104 protocol. Preprocessing steps included normalization, label encoding, and a 70:10:20 train-validation-test split. Seven models, Random Forest, Decision Tree, K-Nearest …

An Efficient Detection And Deep Clustering Based Pipeline For Reliable Rodent Ultrasonic Vocalization Analysis, Sabah S. Anis

Theses and Dissertations

Ultrasonic vocalizations (USVs) are critical for understanding rodents' emotional states and social behaviors. However, manual analysis of USVs is time-consuming, subjective, and prone to errors. This thesis presents an automated pipeline that addresses these challenges by performing efficient USV detection and clustering. The proposed approach significantly reduces the time and effort needed to analyze USV data while improving accuracy and reproducibility.

To address this gap, we introduce ContourUSV, a five-step pipeline for USV detection. First, it begins with generating spectrograms from audio recordings, which are then pre-processed to enhance the contrast between USVs and background noise. Key steps include median …

Hardware Accelerated Simulation Of Buck Converters Using Physics-Informed Neural Networks, James Clayton Crews

Theses and Dissertations

Physics-informed neural networks (PINNs) are an emerging machine learning method for learning the behavior of physical systems described by governing differential equations. Dc-dc power-electronic converters are used in a variety of industry applications such as motor drives or power supplies where real-time simulation is critical for control and safety. This thesis investigates physics-informed machine learning as an approach to develop a real-time digital twin for dc-dc power converters. Traditional numerical integration methods are used to approximate discretized behavior, and the results are compared with a trained PINN model. Modern ML frameworks (such as PyTorch and TensorFlow/Keras) are used to quickly …

Physics Oriented Deep Learning For Material Prediction And Generation, Nihang Fu

Theses and Dissertations

The discovery of new materials is critical to advancing various industries, but traditional experimental methods for materials discovery remain slow and resource-intensive. Recent advances in machine learning (ML), particularly deep learning (DL), have greatly improved and accelerated two main aspects of modern computational material discovery: material design (e.g., material generation) and material screening (e.g., property prediction). However, a key challenge remains: standard ML models often struggle to perform domain-specific tasks effectively. Incorporating domain-specific knowledge, specifically the underlying physics of materials, into ML/DL models is key to improving the accuracy and reliability of material generation and prediction models.

This dissertation discusses …

Elevating Next Generation Wireless Devices Towards Contactless Sensing For Healthcare Applications, Aakriti Adhikari

Theses and Dissertations

There is an increasing interest in technologies that can understand and perceive at-home human activities to provide personalized healthcare monitoring, aimed at early detection of disease markers and assisting physicians in making clinical decisions. Existing approaches, such as wearables, require users to wear sensors that can be cumbersome and cause discomfort. Vision based solutions, such as optical cameras, IRs, LiDARs, etc., can be used to design contactless at-home monitoring systems. However, these systems are limited by poor lighting and occlusion, and they are privacy-invasive. Fortunately, high-frequency millimeter-wave wireless devices provide an effective alternative to the existing systems to enable fine-grained …

Multi-Task Deep Learning Approach For Segmenting And Classifying Competitive Swimming Activities Using A Single Imu, Mark Shperkin

Theses and Dissertations

Competitive swimming performance analysis has traditionally relied on manual video review and multi-sensor systems, both of which are resource-intensive and impractical for everyday training use. This study investigates whether a single wrist-worn inertial measurement unit (IMU) can be used to automatically segment and classify swimming activities with high accuracy. We propose a multi-task deep learning pipeline based on the MTHARS (Multi-Task Human Activity Recognition and Segmentation) architecture introduced by Duan et al. to perform stroke classification, lap segmentation, stroke count estimation, and underwater kick count estimation. Data were collected from eleven collegiate-level swimmers wearing left-wrist-mounted IMUs, each performing five 100-yard …

Explainable Process Recommendation Through Multi-Contextual Grounding Of Dynamic Multimodal Process Knowledge Graphs, Revathy Venkataramanan

Theses and Dissertations

Can I eat this food or not? Is this food suitable for diabetes and why? Which AI pipeline is best suited for a given task and dataset? How should an end-to-end pipeline be constructed? These questions differ from factual question-answering tasks. Recipes and AI pipelines are processes consisting of several entities interacting with each other. A recipe consists of ingredients, cooking methods, and their interactions, while an AI pipeline includes datasets, preprocessing techniques, models, hyperparameters, tasks, and results. Each entity must be analyzed individually, and collective inferencing is performed to derive the final decision. This decision-making process, known as compositional …

Enhancing Proof-Of-Learning Security Against Spoofing Attacks Using Model Watermarking, Ozgur Ural

Doctoral Dissertations and Master's Theses

With the rapid expansion of machine learning (ML) technologies across diverse domains such as healthcare, finance, and autonomous systems, ensuring secure and trustworthy training methodologies has become more critical than ever. Proof-of-Learning (PoL) has recently emerged as a foundational mechanism for verifying the computational effort invested in training ML models, thereby certifying the authenticity and reproducibility of the training process. Yet PoL, when deployed in isolation, remains vulnerable to sophisticated spoofing attacks that manipulate its subset-verification pathways and tolerance parameters. In parallel, model watermarking has become indispensable for safeguarding intellectual property and detecting unauthorized model usage. Motivated by these complementary …

Mtu-Llm: Llm-Based Multi-Robot Task Allocation And Path Planning For Heterogeneous Robots In Search And Rescue Operations, Kaushik Kannan, Jungyun Bae

Michigan Tech Publications

Urban Search and Rescue operations after natural disasters involve locating and assisting victims in hazardous environments, which is challenging. Classical Multi-Robot Task Allocation (MRTA) and path planning approaches have been used to deploy heterogeneous robot teams in unsafe areas. However, existing methods often lack focus on workload balance and requirement fulfillment and struggle to generalize across different scenarios. To address these challenges, we propose Multi-robot Task allocation Utilizing LLMs (MTU-LLM), a framework designed to reduce the development time for task allocation and path planning approaches, enabling faster robot deployment. The framework uses an LLM-based “prompt engineering” approach that generates task …

Sepsis: I Can Catch Your Lies – A New Paradigm For Deception Detection, Anku Rani, Dwip Dalal, Shreya Gautam, Pankaj Gupta, Vinija Jain, Aman Chadha, Amitava Das, Amit P. Sheth

Publications

Deception is the intentional practice of twisting information. It is a nuanced societal practice deeply intertwined with human societal evolution, characterized by a multitude of facets. This research explores the problem of deception through the lens of psychology, employing a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence. The primary focus of this study is specifically on investigating only lies of omission. We propose a novel framework for deception detection leveraging NLP techniques. We curated an annotated dataset of 876,784 samples by amalgamating a popular large-scale fake news dataset and scraped …

Rustmap: Towards Project-Scale C-To-Rust Migration Via Program Analysis And Llm, Xuemeng Cai, Jiakun Liu, Xiping Huang, Yijun Yu, Haitao Wu, Chunmiao Li, Bo Wang, Imam Nur Bani Yusuf, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Migrating existing C programs into Rust is increasingly desired, as Rust offers superior memory safety while maintaining C’s high performance. Existing automated translation tools, such as C2Rust, may rely too much on syntactic, template-based translation and generate unsafe Rust code that is hard for human developers to read, maintain, or even compile. More semantic-aware translation that produces safer, idiomatic, and runnable Rust code is much needed. This paper introduces a novel dependency-guided and large language model (LLM)-based C-to-Rust translation approach, RustMap, based on three key ideas: (1) Utilize LLM’s capabilities to produce idiomatic Rust code from given small pieces of …

Future-Proofing Careers: Unlocking The Potential Of Ai-Driven Digital Badges, Harika Rao

Faculty and Staff Publications & Presentations

This poster explores the transformative role of AI-driven digital badges and microcredentials in addressing the urgent need for adaptable, workforce-ready graduates in an era of rapid technological change. By offering personalized, stackable, and industry-aligned credentials, higher education institutions can empower learners with just-in-time skills that traditional degree programs often fail to provide. This poster highlights how AI can support granular competency assessment, flexible online delivery, and lifelong learning pathways, enabling students to showcase evidence of skill mastery in ways that are both affordable and scalable.