Author name cluster

Hung Nguyen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

1 author row

AAAI Conference 2025 Conference Paper

SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models

Hung Nguyen
Quang Qui-Vinh Nguyen
Khoi Nguyen
Rang Nguyen

Given an input video of a person and a new garment, the objective of this paper is to synthesize a new video where the person is wearing the specified garment while maintaining spatiotemporal consistency. Although significant advances have been made in image-based virtual try-on, extending these successes to video often leads to frame-to-frame inconsistencies. Some approaches have attempted to address this by increasing the overlap of frames across multiple video chunks, but this comes at a steep computational cost due to the repeated processing of the same frames, especially for long video sequences. To tackle these challenges, we reconceptualize video virtual try-on as a conditional video inpainting task, with garments serving as input conditions. Specifically, our approach enhances image diffusion models by incorporating temporal attention layers to improve temporal coherence. To reduce computational overhead, we propose ShiftCaching, a novel technique that maintains temporal consistency while minimizing redundant computations. Furthermore, we introduce the TikTokDress dataset, a new video try-on dataset featuring more complex backgrounds, challenging movements, and higher resolution compared to existing public datasets. Extensive experiments demonstrate that our approach outperforms current baselines, particularly in terms of video consistency and inference speed.

PDF Details DOI

JBHI Journal 2024 Journal Article

Combining Multistaged Filters and Modified Segmentation Network for Improving Lung Nodules Classification

Rudy Gunawan
Yvonne Tran
Jinchuan Zheng
Hung Nguyen
Ann Carrigan
Megan K. Mills
Rifai Chai

Advancements in computational technology have led to a shift towards automated detection processes in lung cancer screening, particularly through nodule segmentation techniques. These techniques employ thresholding to distinguish between soft and firm tissues, including cancerous nodules. The challenge of accurately detecting nodules close to critical lung structures such as blood vessels, bronchi, and the pleura highlights the necessity for more sophisticated methods to enhance diagnostic accuracy. This paper proposed combined processing filters for data preparation before using one of the modified Convolutional Neural Networks (CNNs) as the classifier. With refined filters, the nodule targets are solid, semi-solid, and ground glass, ranging from low-stage cancer (cancer screening data) to high-stage cancer. Furthermore, two additional works were added to address juxta-pleural nodules while the pre-processing end and classification are done in a 3-dimensional domain in opposition to the usual image classification. The accuracy output indicates that even using a simple Segmentation Network if modified correctly, can improve the classification result compared to the other eight models. The proposed sequence total accuracy reached 99. 7%, with 99. 71% cancer class accuracy and 99. 82% non-cancer accuracy, much higher than any previous research, which can improve the detection efforts of the radiologist.

Details DOI

IJCAI Conference 2024 Conference Paper

LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks

Hung Nguyen
Tobias Clement
Loc Nguyen
Nils Kemmerzell
Binh Truong
Khang Nguyen
Mohamed Abdelaal
Hung Cao

LangXAI is a framework that integrates Explainable Artificial Intelligence (XAI) with advanced vision models to generate textual explanations for visual recognition tasks. Despite XAI advancements, an understanding gap persists for end-users with limited domain knowledge in artificial intelligence and computer vision. LangXAI addresses this by furnishing text-based explanations for classification, object detection, and semantic segmentation model outputs to end-users. Preliminary results demonstrate LangXAI's enhanced plausibility, with high BERTScore across tasks, fostering a more transparent and reliable AI framework on vision tasks for end-users. The code and demo of this work can be found at https: //analytics-everywhere-lab. github. io/langxai. io/.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Limited Query Graph Connectivity Test

Mingyu Guo
Jialiang Li
Aneta Neumann
Frank Neumann
Hung Nguyen

We propose a combinatorial optimisation model called Limited Query Graph Connectivity Test. We consider a graph whose edges have two possible states (On/Off). The edges' states are hidden initially. We could query an edge to reveal its state. Given a source s and a destination t, we aim to test s−t connectivity by identifying either a path (consisting of only On edges) or a cut (consisting of only Off edges). We are limited to B queries, after which we stop regardless of whether graph connectivity is established. We aim to design a query policy that minimizes the expected number of queries. Our model is mainly motivated by a cyber security use case where we need to establish whether attack paths exist in a given network, between a source (i.e., a compromised user node) and a destination (i.e., a high-privilege admin node). Edge query is resolved by manual effort from the IT admin, which is the motivation behind query minimization. Our model is highly related to Stochastic Boolean Function Evaluation (SBFE). There are two existing exact algorithms for SBFE that are prohibitively expensive. We propose a signifcantly more scalable exact algorithm. While previous exact algorithms only scale for trivial graphs (i.e., past works experimented on at most 20 edges), we empirically demonstrate that our algorithm is scalable for a wide range of much larger practical graphs (i.e., graphs representing Windows domain networks with tens of thousands of edges). We also propose three heuristics. Our best-performing heuristic is via limiting the planning horizon of the exact algorithm. The other two are via reinforcement learning (RL) and Monte Carlo tree search (MCTS). We also derive an algorithm for computing the performance lower bound. Experimentally, we show that all our heuristics are near optimal. The heuristic building on the exact algorithm outperforms all other heuristics, surpassing RL, MCTS and eight existing heuristics ported from SBFE and related literature.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Practical Anytime Algorithms for Judicious Partitioning of Active Directory Attack Graphs

Yumeng Zhang
Max Ward
Hung Nguyen

Given a directed graph, a set of source nodes, a target node and a budget, we study the problem of maximizing the number of source nodes disconnected from the target node by removing edges not exceeding the budget. Our model is mainly motivated by a cyber security use case where we need to minimize the attack surface of a Windows Active Directory system. In these high-profile attacks, the attackers first compromise a source (i. e. , a compromised user node) and then laterally move to a destination (i. e. , a high-privileged admin node). Our aim is to minimize the number of users with a path to the admin. We first prove that the problem is NP-hard. Algorithms for exact optimality usually struggle to converge on graphs that approach real-world network scales and therefore are not practical for usage. In light of this, we study anytime algorithms that return an acceptable result whenever the algorithm is terminated, and can improve optimality by allowing longer computational time. We observe the source connectivity of directed graphs, based on which we propose a novel anytime algorithm---the spiral algorithm. We also develop two Monte Carlo Tree Search (MCTS) algorithms as a baseline to study the performance of typical anytime algorithms for our problem, and show that the spiral algorithm improves the optimality at a significantly faster speed and therefore exhibits better anytime behavior compared with MCTS.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Near Optimal Strategies for Honeypots Placement in Dynamic and Large Active Directory Networks

Huy Q. Ngo
Mingyu Guo
Hung Nguyen

Active Directory (AD) is the default security management system for Windows domain networks and is the target of many recent cyber attacks. We study a Stackelberg game between an attacker and a defender on large Active Directory (AD) attack graphs, where the defender employs a set of honeypots to stop the attacker from reaching high value targets. Contrary to existing works that focus on small and static attack graphs, AD graphs typically contain hundreds of thousands of nodes/edges and constantly change over time. We show that the optimal honeypot placement problem is NP-hard even for static graphs and develop a tree decomposition method to derive an optimal deployment strategy and a mixedinteger programming (MIP) formulation to scale to large graphs. We observed that the optimal blocking plan for static graphs performs poorly for dynamic graphs. To handle dynamic graphs, we re-design the mixed-integer programming formulation by combining m MIP (dyMIP(m)) instances. We prove a performance lower-bound on the optimal blocking strategy for dynamic graphs and show that our dyMIP(m) algorithm produces near optimal results.

PDF

AAAI Conference 2023 Conference Paper

Scalable Edge Blocking Algorithms for Defending Active Directory Style Attack Graphs

Mingyu Guo
Max Ward
Aneta Neumann
Frank Neumann
Hung Nguyen

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment naturally describes an attack graph where nodes represent computers/accounts/security groups, and edges represent existing accesses/known exploits that allow the attacker to gain access from one node to another. Motivated by practical AD use cases, we study a Stackelberg game between one attacker and one defender. There are multiple entry nodes for the attacker to choose from and there is a single target (Domain Admin). Every edge has a failure rate. The attacker chooses the attack path with the maximum success rate. The defender can block a limited number of edges (i.e., revoke accesses) from a set of blockable edges, limited by budget. The defender's aim is to minimize the attacker's success rate. We exploit the tree-likeness of practical AD graphs to design scalable algorithms. We propose two novel methods that combine theoretical fixed parameter analysis and practical optimisation techniques. For graphs with small tree widths, we propose a tree decomposition based dynamic program. We then propose a general method for converting tree decomposition based dynamic programs to reinforcement learning environments, which leads to an anytime algorithm that scales better, but loses the optimality guarantee. For graphs with small numbers of non-splitting paths (a parameter we invent specifically for AD graphs), we propose a kernelization technique that significantly downsizes the model, which is then solved via mixed-integer programming. Experimentally, our algorithms scale to handle synthetic AD graphs with tens of thousands of nodes.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Practical Fixed-Parameter Algorithms for Defending Active Directory Style Attack Graphs

Mingyu Guo
Jialiang Li
Aneta Neumann
Frank Neumann
Hung Nguyen

Active Directory is the default security management system for Windows domain networks. We study the shortest path edge interdiction problem for defending Active Directory style attack graphs. The problem is formulated as a Stackelberg game between one defender and one attacker. The attack graph contains one destination node and multiple entry nodes. The attacker’s entry node is chosen by nature. The defender chooses to block a set of edges limited by his budget. The attacker then picks the shortest unblocked attack path. The defender aims to maximize the expected shortest path length for the attacker, where the expectation is taken over entry nodes. We observe that practical Active Directory attack graphs have small maximum attack path lengths and are structurally close to trees. We first show that even if the maximum attack path length is a constant, the problem is still W[1]-hard with respect to the defender’s budget. Having a small maximum attack path length and a small budget is not enough to design fixed-parameter algorithms. If we further assume that the number of entry nodes is small, then we derive a fixedparameter tractable algorithm. We then propose two other fixed-parameter algorithms by exploiting the tree-like features. One is based on tree decomposition and requires a small tree width. The other assumes a small number of splitting nodes (nodes with multiple outgoing edges). Finally, the last algorithm is converted into a graph convolutional neural network based heuristic, which scales to larger graphs with more splitting nodes.

PDF Details

JBHI Journal 2016 Journal Article

Hypotension Risk Prediction via Sequential Contrast Patterns of ICU Blood Pressure

Shameek Ghosh
Mengling Feng
Hung Nguyen
Jinyan Li

Acute hypotension is a significant risk factor for in-hospital mortality at intensive care units. Prolonged hypotension can cause tissue hypoperfusion, leading to cellular dysfunction and severe injuries to multiple organs. Prompt medical interventions are thus extremely important for dealing with acute hypotensive episodes (AHE). Population level prognostic scoring systems for risk stratification of patients are suboptimal in such scenarios. However, the design of an efficient risk prediction system can significantly help in the identification of critical care patients, who are at risk of developing an AHE within a future time span. Toward this objective, a pattern mining algorithm is employed to extract informative sequential contrast patterns from hemodynamic data, for the prediction of hypotensive episodes. The hypotensive and normotensive patient groups are extracted from the MIMIC-II critical care research database, following an appropriate clinical inclusion criteria. The proposed method consists of a data preprocessing step to convert the blood pressure time series into symbolic sequences, using a symbolic aggregate approximation algorithm. Then, distinguishing subsequences are identified using the sequential contrast mining algorithm. These subsequences are used to predict the occurrence of an AHE in a future time window separated by a user-defined gap interval. Results indicate that the method performs well in terms of the prediction performance as well as in the generation of sequential patterns of clinical significance. Hence, the novelty of sequential patterns is in their usefulness as potential physiological biomarkers for building optimal patient risk stratification systems and for further clinical investigation of interesting patterns in critical care patients.

Details DOI

EAAI Journal 2016 Journal Article

Quality and robustness improvement for real world industrial systems using a fuzzy particle swarm optimization

Sai Ho Ling
Kit Yan Chan
Frank Hung Fat Leung
Frank Jiang
Hung Nguyen

This paper presents a novel fuzzy particle swarm optimization with cross-mutated (FPSOCM) operation, where a fuzzy logic system developed based on the knowledge of swarm intelligence is proposed to determine the inertia weight for the swarm movement of particle swarm optimization (PSO) and the control parameter of a newly introduced cross-mutated operation. Hence, the inertia weight of the PSO can be adaptive with respect to the search progress. The new cross-mutated operation intends to drive the solution to escape from local optima. A suite of benchmark test functions are employed to evaluate the performance of the proposed FPSOCM. Experimental results show empirically that the FPSOCM performs better than the existing hybrid PSO methods in terms of solution quality, robustness, and convergence rate. The proposed FPSOCM is evaluated by improving the quality and robustness of two real world industrial systems namely economic load dispatch system and self-provisioning systems for communication network services. These two systems are employed to evaluate the effectiveness of the proposed FPSOCM as they are multi-optima and non-convex problems. The performance of FPSOCM is found to be significantly better than that of the existing hybrid PSO methods in a statistical sense. These results demonstrate that the proposed FPSOCM is a good candidate for solving product or service engineering problems which have multi-optima or non-convex natures.

Details DOI

AIIM Journal 2014 Journal Article

Advanced portable remote monitoring system for the regulation of treadmill running exercises

Tuan Nghia Nguyen
Steven Su
Branko Celler
Hung Nguyen

Objective This study aims to develop an advanced portable remote monitoring system to supervise high intensity treadmill exercises. Materials and methods The supervisory level of the developed hierarchical system is implemented on a portable monitoring device (iPhone/iPad) as a client application, while the real-time control of treadmill exercises is accomplished by using an on-line adaptive neural network control scheme in a local computer system. During training or rehabilitation exercises, the intensity (measured by heart rate) is regulated by simultaneously manipulating both treadmill speed and gradient. In order to achieve adaptive tracking performance, a neural network controller has been designed and implemented. Results Six real-time experiments have been conducted to test the performance of the developed monitoring system. Experimental results obtained in real-time with heart-rate set-point varying from 145bpm to 180bmp, demonstrate that the proposed system can quickly and accurately regulate exercise intensity of treadmill running exercises with desired performance (no overshoot, settling time T s ≤100s). Subjects aged from 29 to 38 years old participated in different set-point experiments to confirm the system's adaptability to inter- and intra-model uncertainty. The desired system performance under external disturbances has also been confirmed in a final real-time experiment demonstrating a user carrying the 10kg bag then removing it during the exercise. Conclusion In contrast with conventional control approaches, the proposed adaptive controller achieves better heart rate tracking performance under inter- and intra-model uncertainty and external disturbances. The developed system can automatically adapt to various individual exercisers and a range of exercise intensity.

Details DOI

AAAI Conference 2014 Conference Paper

Spatio-Temporal Consistency as a Means to Identify Unlabeled Objects in a Continuous Data Field

James Faghmous
Hung Nguyen
Matthew Le
Vipin Kumar

Mesoscale ocean eddies are a critical component of the Earth System as they dominate the ocean’s kinetic energy and impact the global distribution of oceanic heat, salinity, momentum, and nutrients. Therefore, accurately representing these dynamic features is critical for our planet’s sustainability. The majority of methods that identify eddies from satellite observations analyze the data in a frame-by-frame basis despite the fact that eddies are dynamic objects that propagate across space and time. We introduce the notion of spatio-temporal consistency to identify eddies in a continuous spatiotemporal field, to simultaneously ensure that the features detected are both spatially and temporally consistent. Our spatio-temporal consistency approach allows us to remove most of the expert criteria used in traditional methods to reduce false negatives. The removal of arbitrary heuristics enables us to render more complete eddy dynamics by identifying smaller and longer lived eddies compared to existing methods.

PDF Details