Computer Sciences Commons^™

Unbiased Multiple Instance Learning For Weakly Supervised Video Anomaly Detection, Hui Lyu, Zhongqi Yue, Qianru Sun, Bin Luo, Zhen Cui, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training …

Improving The Efficiency Of Exponential Ratio-Type Estimator For Population Median: A Calibration Weight Adjustment Approach, Mathew J. Iseh, Kufre J. Bassey

CBN Journal of Applied Statistics (JAS)

This paper modifies the Bahl and Tuteja exponential ratio-type estimator for population median under simple random and stratified sampling schemes using calibration weight adjustment technique with supplementary information to vary the stratum weights. The bias and mean square error of the modified estimator were obtained up to the second-order approximation, which satisfies the necessary conditions for efficiency. The findings show that the new estimator surpasses existing estimators in efficiency gain. This suggests the appropriateness of calibration weight modification in boosting the efficiency of a population parameter estimator under stratified random sampling especially where the population parameter of the auxiliary variable …

Knowledge Compilation For Constrained Combinatorial Action Spaces In Reinforcement Learning, Jiajing Ling, Moritz Lukas Schuler, Akshat Kumar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Action-constrained reinforcement learning (ACRL), where any action taken in a state must satisfy given constraints, has several practical applications such as resource allocation in supply-demand matching, and path planning among others. A key challenge is to enforce constraints when the action space is discrete and combinatorial. To address this, first, we assume an action is represented using propositional variables, and action constraints are represented using Boolean functions. Second, we compactly encode the set of all valid actions that satisfy action constraints using a probabilistic sentential decision diagram (PSDD), a recently proposed knowledge compilation framework. Parameters of the PSDD compactly encode …

Ifundit: Visual Profiling Of Fund Investment Styles, Rong Zhang, Bon Kyung Ku, Yong Wang, Xuanwu Yue, Siyuan Liu, Ke Li, Huamin Qu

Research Collection School Of Computing and Information Systems

Mutual funds are becoming increasingly popular with the emergence of Internet finance. Clear profiling of a fund's investment style is crucial for fund managers to evaluate their investment strategies, and for investors to understand their investment. However, it is challenging to profile a fund's investment style as it requires a comprehensive analysis of complex multi-dimensional temporal data. In addition, different fund managers and investors have different focuses when analysing a fund's investment style. To address the issue, we propose iFUNDit, an interactive visual analytic system for fund investment style analysis. The system decomposes a fund's critical features into performance attributes …

Mosaic: Spatially-Multiplexed Edge Ai Optimization Over Multiple Concurrent Video Sensing Streams, Ila Gokarn, Hemanth Sabbella, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and complexity of DNN models. One promising approach involves criticality-aware processing, where the computation is directed selectively to "critical" portions of individual image frames. We introduce MOSAIC, a novel system for such criticality-aware concurrent processing of multiple vision sensing streams that provides a multiplicative increase in the achievable throughput with negligible loss in perception fidelity. MOSAIC determines critical regions from images received from multiple vision …

Catching The Fast Payments Trend: Optimal Designs And Leadership Strategies Of Retail Payment And Settlement Systems, Zhiling Guo, Dan Ma

Research Collection School Of Computing and Information Systems

Recent financial technologies have enabled fast payments and are reshaping retail payment and settlement systems globally. We developed an analytical model to study the optimal design of a new retail payment system in terms of settlement speed and system capability under both bank and fintech firm heterogeneous participation incentives. We found that three types of payment systems emerge as equilibrium outcomes: batch retail (BR), expedited retail (ER), and real-time retail (RR) payment systems. Although the base value of the payment service positively affects both settlement speed and system capability, the expected liquidity cost negatively impacts settlement speed, and total transaction …

Glocal Energy-Based Learning For Few-Shot Open-Set Recognition, Haoyu Wang, Guansong Pang, Peng Wang, Lei Zhang, Wei Wei, Yanning Zhang

Research Collection School Of Computing and Information Systems

Few-shot open-set recognition (FSOR) is a challenging task of great practical value. It aims to categorize a sample to one of the pre-defined, closed-set classes illustrated by few examples while being able to reject the sample from unknown classes. In this work, we approach the FSOR task by proposing a novel energy-based hybrid model. The model is composed of two branches, where a classification branch learns a metric to classify a sample to one of closedset classes and the energy branch explicitly estimates the open-set probability. To achieve holistic detection of openset samples, our model leverages both class-wise and pixelwise …

Freestyle Layout-To-Image Synthesis, Han Xue, Zhiwu Huang, Qianru Sun, Li Song, Wenjun Zhang

Research Collection School Of Computing and Information Systems

Typical layout-to-image synthesis (LIS) models generate images for a close set of semantic classes, e.g., 182 common objects in COCO-Stuff. In this work, we explore the freestyle capability of the model, i.e., how far can it generate unseen semantics (e.g., classes, attributes, and styles) onto a given layout, and call the task Freestyle LIS (FLIS). Thanks to the development of large-scale pre-trained language-image models, a number of discriminative models (e.g., image classification and object detection) trained on limited base classes are empowered with the ability of unseen class prediction. Inspired by this, we opt to leverage large-scale pre-trained text-to-image diffusion …

Improving Quantal Cognitive Hierarchy Model Through Iterative Population Learning, Yuhong Xu, Shih-Fen Cheng, Xinyu Chen

Research Collection School Of Computing and Information Systems

In this paper, we propose to enhance the state-of-the-art quantal cognitive hierarchy (QCH) model with iterative population learning (IPL) to estimate the empirical distribution of agents’ reasoning levels and fit human agents’ behavioral data. We apply our approach to a real-world dataset from the Swedish lowest unique positive integer (LUPI) game and show that our proposed approach outperforms the theoretical Poisson Nash equilibrium predictions and the QCH approach by 49.8% and 46.6% in Wasserstein distance respectively. Our approach also allows us to explicitly measure an agent’s reasoning level distribution, which is not previously possible.

A Mixed-Integer Linear Programming Reduction Of Disjoint Bilinear Programs Via Symbolic Variable Elimination, Jihwan Jeong, Scott Sanner, Akshat Kumar

Research Collection School Of Computing and Information Systems

A disjointly constrained bilinear program (DBLP) has various practical and industrial applications, e.g., in game theory, facility location, supply chain management, and multi-agent planning problems. Although earlier work has noted the equivalence of DBLP and mixed-integer linear programming (MILP) from an abstract theoretical perspective, a practical and exact closed-form reduction of a DBLP to a MILP has remained elusive. Such explicit reduction would allow us to leverage modern MILP solvers and techniques along with their solution optimality and anytime approximation guarantees. To this end, we provide the first constructive closed-form MILP reduction of a DBLP by extending the technique of …

How To Resuscitate A Sick Vm In The Cloud, Xuhua Ding

Research Collection School Of Computing and Information Systems

A guest virtual machine in a cloud platform may fall “sick” when its kernel encounters a fatal low-level bug or is subverted by an adversary. The VM owner is hence likely to lose her control over it due to a kernel hang or being denied of remote accesses. While the VM can be rebooted with the assistance from the cloud server, the owner not only faces service disruption but also is left with no opportunity to make an in-depth diagnosis and forensics on the spot, not to mention a live rectification. Currently, the cloud service provider has neither incentive nor …

Livoauth: Liveness Detection In Voiceprint Authentication With Random Challenges And Detection Modes, Rui Zhang, Zheng Yan, Xueru Wang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Voiceprint authentication provides great convenience to users in many application scenarios. However, it easily suffers from spoofing attacks including speech synthesis, speech conversion, and speech replay. Liveness detection is an effective way to resist these attacks. But existing methods suffer from many disadvantages, such as extra deployment costs due to precise data collection, environmental disturbance, high computational overhead, and operational complexity. A uniform platform that can offer voiceprint authentication as a service (VAaS) over the cloud is also lacked. Hence, it is imperative to design an economic and effective method for liveness detection in voiceprint authentication. In this article, we …

Evading Deepfake Detectors Via Adversarial Statistical Consistency, Yang Hou, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds, more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences between natural (i.e., real) and DeepFake-generated images in both spatial and frequency domains. In this work, we propose to explicitly minimize the statistical differences to evade state-of-the-art DeepFake detectors. To this end, we propose a statistical consistency attack (StatAttack) against DeepFake detectors, which contains two main parts. First, we select several statistical-sensitive natural degradations (i.e., exposure, blur, and noise) and add them to the fake images …

The Bemi Stardust: A Structured Ensemble Of Binarized Neural Networks, Ambrogio Maria Bernardelli, Stefano Gualandi, Hoong Chuin Lau, Simone Milanesi

Research Collection School Of Computing and Information Systems

Binarized Neural Networks (BNNs) are receiving increasing attention due to their lightweight architecture and ability to run on low-power devices, given the fact that they can be implemented using Boolean operations. The state-of-the-art for training classification BNNs restricted to few-shot learning is based on a Mixed Integer Programming (MIP) approach. This paper proposes the BeMi ensemble, a structured architecture of classification-designed BNNs based on training a single BNN for each possible pair of classes and applying a majority voting scheme to predict the final output. The training of a single BNN discriminating between two classes is achieved by a MIP …

Law Smells: Defining And Detecting Problematic Patterns In Legal Drafting, Corinna Coupette, Dirk Hartung, Janis Beckedorf, Maximilian Böther, Daniel Martin Katz

Research Collection Yong Pung How School Of Law

Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running examples—namely, duplicated phrase, long element, large reference tree, ambiguous syntax, and natural language obsession—, we develop a comprehensive law smell taxonomy. This taxonomy classifies law smells by when they can be detected, which aspects of law they relate to, and how they can be discovered. We introduce textbased and graph-based methods to identify instances of law smells, confirming their utility in …

Law Smells: Defining And Detecting Problematic Patterns In Legal Drafting, Corinna Coupette, Dirk Hartung, Janis Beckedorf, Maximilian Bother, Daniel Martin Katz

Research Collection Yong Pung How School Of Law

Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running examples—namely, duplicated phrase, long element, large reference tree, ambiguous syntax, and natural language obsession—, we develop a comprehensive law smell taxonomy. This taxonomy classifies law smells by when they can be detected, which aspects of law they relate to, and how they can be discovered. We introduce text-based and graph-based methods to identify instances of law smells, confirming their utility in …

Ocapo: Occupancy-Aware, Pdc Control For Open-Plan, Shared Workspaces, Anaradha Ravi, Archan Misra

Research Collection School Of Computing and Information Systems

Passive Displacement Cooling (PDC) has gained popularity as a means of significantly reducing building energy consumption overheads, especially in tropical climates. PDC eliminates the use of mechanical fans, instead using chilled-water heat exchangers to perform convective cooling. In this paper, we evaluate the impact of different parameters affecting occupant comfort in a 1000m2 open-floor area (consisting of multiple zones) of a ZEB (Zero Energy Building) deployed with PDC units and tackle the problem of setting the temperature setpoint of the PDC units to assure occupant thermal comfort. We tackle two key practical challenges: (a) the zone-level (i.e., occupant-experienced) temperature differs …

Multi-Head Attention Graph Convolutional Network Model: End-To-End Entity And Relation Joint Extraction Based On Multi-Head Attention Graph Convolutional Network, Zhihua Tao, Chunping Ouyang, Yongbin Liu, Tonglee Chung, Yixin Cao

Research Collection School Of Computing and Information Systems

At present, the entity and relation joint extraction task has attracted more and more scholars' attention in the field of natural language processing (NLP). However, most of their methods rely on NLP tools to construct dependency trees to obtain sentence structure information. The adjacency matrix constructed by the dependency tree can convey syntactic information. Dependency trees obtained through NLP tools are too dependent on the tools and may not be very accurate in contextual semantic description. At the same time, a large amount of irrelevant information will cause redundancy. This paper presents a novel end-to-end entity and relation joint extraction …

Groundnlq @ Ego4d Natural Language Queries Challenge 2023, Zhijian Hou, Lei Ji, Difei Gao, Wanjun Zhong, Kun Yan, Chong-Wah Ngo, Wing-Kwong Chan, Chong-Wah Ngo, Nan Duan, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data. In addition, we introduce a novel grounding model GroundNLQ, which employs a multi-modal multiscale grounding module for effective video and text fusion and various temporal intervals, especially for long videos. On the blind test …

Distpreserv: Maintaining User Distribution For Privacy-Preserving Location-Based Services, Yanbing Ren, Xinghua Li, Yinbin Miao, Robert H. Deng, Jian Weng, Siqi Ma, Jianfeng Ma

Research Collection School Of Computing and Information Systems

Location-Based Services (LBSs) are one of the most frequently used mobile applications in the modern society. Geo-Indistinguishability (Geo-Ind) is a promising privacy protection model for LBSs since it can provide formal security guarantees for location privacy. However, Geo-Ind undermines the statistical location distribution of users on the LBS server because of perturbed locations, thereby disabling the server to provide distribution-based services (e.g., traffic congestion maps). To overcome this issue, we give a privacy definition, called DistPreserv, to enable the LBS server to acquire valid location distributions while providing users with strict location protection. Then we propose a privacy-preserving LBS scheme …

Towards A Smaller Student: Capacity Dynamic Distillation For Efficient Image Retrieval, Yi Xie, Huaidong Zhang, Xuemiao Xu, Jianqing Zhu, Shengfeng He

Research Collection School Of Computing and Information Systems

Previous Knowledge Distillation based efficient image retrieval methods employ a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective knowledge imitation during the most critical early training period, causing final performance degeneration. To tackle this issue, we propose a Capacity Dynamic Distillation framework, which constructs a student model with editable representation capacity. Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the student model is gradually compressed during the training. To dynamically adjust the model capacity, our …

Avoiding Starvation Of Arms In Restless Multi-Armed Bandit, Dexun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Restless multi-armed bandits (RMAB) is a popular framework for optimizing performance with limited resources under uncertainty. It is an extremely useful model for monitoring beneficiaries (arms) and executing timely interventions using health workers (limited resources) to ensure optimal benefit in public health settings. For instance, RMAB has been used to track patients' health and monitor their adherence in tuberculosis settings, ensure pregnant mothers listen to automated calls about good pregnancy practices, etc. Due to the limited resources, typically certain individuals, communities, or regions are starved of interventions, which can potentially have a significant negative impact on the individual/community in the …

Enhancing Third-Party Software Reliability Through Bug Bounty Programs, Tianlu Zhou, Dan Ma, Nan Feng

Research Collection School Of Computing and Information Systems

Bug Bounty Programs (BBPs) reward external hackers for identifying and reporting software vulnerabilities. As the number of security issues caused by third-party applications has been significantly increased recently, many digital platforms are considering launching BBPs to help enhance the reliability of third-party software. BBPs bring benefits to the platform and vendors, meanwhile impose additional costs on them as well. As a result, the overall impact of using BBP is unclear. In this paper, we present an analytical model to examine the strategic decisions of launching and participating in a BBP for the platform and the third-party vendor, respectively. We find …

3d Dental Biometrics: Transformer-Based Dental Arch Extraction And Matching, Zhiyuan Zhang, Zhong Xin

Research Collection School Of Computing and Information Systems

The dental arch is a significant anatomical feature that is crucial in assessing tooth arrangement and configuration and has a potential for human identification in biometrics and digital forensic dentistry. In a previous study, we proposed an auto pose-invariant arch feature extraction Radial Ray Algorithm (RRA) and a matching framework [1] based solely on 3D dental geometry. To enhance the identification accuracy and speed of our previous work, we propose in this study a transformer architecture that can extract dental keypoints by encoding both local and global features. The dental arch is then constructed through robust interpolation of the dental …

Towards Explaining Sequences Of Actions In Multi-Agent Deep Reinforcement Learning Models, Phyo Wai Khaing, Minghong Geng, Budhitama Subagdja, Shubham Pateria, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Although Multi-agent Deep Reinforcement Learning (MADRL) has shown promising results in solving complex real-world problems, the applicability and reliability of MADRL models are often limited by a lack of understanding of their inner workings for explaining the decisions made. To address this issue, this paper proposes a novel method for explaining MADRL by generalizing the sequences of action events performed by agents into high-level abstract strategies using a spatio-temporal neural network model. Specifically, an interval-based memory retrieval procedure is developed to generalize the encoded sequences of action events over time into short sequential patterns. In addition, two abstraction algorithms are …

Semantic Scene Completion With Cleaner Self, Fengyun Wang, Dong Zhang, Hanwang Zhang, Jinhui Tang, Qianru Sun

Research Collection School Of Computing and Information Systems

Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to “imagine” what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels to generate a perfect visible surface, …

Deep Learning Recommendations For The Acl2 Interactive Theorem Prover, Robert K. Thompson, Robert K. Thompson

Master's Theses

Due to the difficulty of obtaining formal proofs, there is increasing interest in partially or completely automating proof search in interactive theorem provers. Despite being a theorem prover with an active community and plentiful corpus of 170,000+ theorems, no deep learning system currently exists to help automate theorem proving in ACL2. We have developed a machine learning system that generates recommendations to automatically complete proofs. We show that our system benefits from the copy mechanism introduced in the context of program repair. We make our system directly accessible from within ACL2 and use this interface to evaluate our system in …

An Efficient Strategy For Deploying Deception Technology, Noora Abdulla Alhosani

Theses

Implementations of deception technology is crucial in discovering attacks by creating a controlled and monitored environment for detecting malicious activity. This technology involves the deployment of decoys, traps, and honeypots that mimic natural systems and network assets to attract and identify attackers. The use of deception technology provides an early warning system for detecting cyber-attacks, allowing organizations to respond quickly and mitigate damage. This article proposed a framework that focuses on maximizing the efficiency of deception technology in detecting sophisticated attacks. The framework employs multi-layered deception techniques at various levels of the network, system, and application to provide comprehensive coverage …

Machine Learning And Network Embedding Methods For Gene Co-Expression Networks, Niloofar Aghaieabiane

Dissertations

High-throughput technologies such as DNA microarrays and RNA-seq are used to measure the expression levels of large numbers of genes simultaneously. To support the extraction of biological knowledge, individual gene expression levels are transformed into Gene Co-expression Networks (GCNs). GCNs are analyzed to discover gene modules. GCN construction and analysis is a well-studied topic, for nearly two decades. While new types of sequencing and the corresponding data are now available, the software package WGCNA and its most recent variants are still widely used, contributing to biological discovery.

The discovery of biologically significant modules of genes from raw expression data is …

Trustworthy Machine Learning Through The Lens Of Privacy And Security, Thi Kim Phung Lai

Dissertations

Nowadays, machine learning (ML) becomes ubiquitous and it is transforming society. However, there are still many incidents caused by ML-based systems when ML is deployed in real-world scenarios. Therefore, to allow wide adoption of ML in the real world, especially in critical applications such as healthcare, finance, etc., it is crucial to develop ML models that are not only accurate but also trustworthy (e.g., explainable, privacy-preserving, secure, and robust). Achieving trustworthy ML with different machine learning paradigms (e.g., deep learning, centralized learning, federated learning, etc.), and application domains (e.g., computer vision, natural language, human study, malware systems, etc.) is challenging, …