LNLuan Viet Nguyen

Luan Viet Nguyen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Luan Viet Nguyen has a total of 62 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Quantitative Verification for Temporal Properties of Massive Linear Systems

    by Qing Liu, Yuntao Li, Sung Woo Choi, Luan Viet Nguyen, Hoang-Dung Tran

  • Open Access

    Hyperproperty-Constrained Secure Reinforcement Learning

    by Ernest Bonnah, Luan Nguyen, Khaza Anuarul Hoque

  • Open Access

    Reachability Analysis of Sigmoidal Neural Networks

    by Sung Woo Choi, Mykhailo Ivashchenko, Luan V. Nguyen, Dung Tran

    This paper extends the star set reachability approach to verify the robustness of feed-forward neural networks (FNNs) with sigmoidal activation functions such as Sigmoid and TanH. The main drawbacks of the star set approach in Sigmoid/TanH FNN verification are scalability, feasibility, and optimality issues in some cases due to the linear programming solver usage. We overcome this challenge by proposing a relaxed star (RStar) with symbolic intervals, which allows the usage of the back-substitution technique in DeepPoly to find bounds when overapproximating activation functions while maintaining the valuable features of a star set. RStar can overapproximate a sigmoidal activation function using four linear constraints (RStar4) or two linear constraints (RStar2), or only the output bounds (RStar0). We implement our RStar reachability algorithms in NNV and compare them to DeepPoly via robustness verification of image classification DNNs benchmarks. The experimental results show that the original star approach (i.e., no relaxation) is the least conservative of all methods yet the slowest. RStar4 is computationally much faster than the original star method and is the second least conservative approach. It certifies up to 40% more images against adversarial attacks than DeepPoly and on average 51 times faster than the star set. Last but not least, RStar0 is the most conservative method, which could only verify two cases for the CIFAR10 small Sigmoid network, δ = 0.014. However, it is the fastest method that can verify neural networks up to 3528 times faster than the star set and up to 46 times faster than DeepPoly in our evaluation.


  • Efficient SMT-Based Model Checking for HyperTWTL

    by Ernest Bonnah, Luan Viet Nguyen, Khaza Anuarul Hoque

  • Open Access

    A Parallel Gumbel-Softmax VAE Framework with Performance-Based Tuning

    by Fangshi Zhou, Tianming Zhao, Luan Viet Nguyen, Zhongmei Yao

    Traditional training algorithms for Gumbel Softmax Variational Autoencoders (GS-VAEs) typically rely on an annealing scheme that gradually reduces the Softmax temperature τ according to a given function. This approach can lead to suboptimal results. To improve the performance, we propose a parallel framework for GS-VAEs, which embraces dual latent layers and multiple sub-models with diverse temperature strategies. Instead of relying on a fixed function for adjusting τ, our training algorithm uses loss difference as performance feedback to dynamically update each sub-model’s temperature τ, which is inspired by the need to balance exploration and exploitation in learning. By combining diversity in temperature strategies with the performance-based tuning method, our design helps prevent sub-models from becoming trapped in local optima and finds the GS-VAE model that best fits the given dataset. In experiments using four classic image datasets, our model significantly surpasses a standard GS-VAE that employs a temperature annealing scheme across multiple tasks, including data reconstruction, generalization capabilities, anomaly detection, and adversarial robustness. Our implementation is publicly available at https://github.com/wxzg7045/Gumbel-Softmax-VAE-2024/tree/main.


  • Open Access

    Model Checking Time Window Temporal Logic for Hyperproperties

    by Ernest Bonnah, Luan Nguyen, Khaza Anuarul Hoque

    Hyperproperties extend trace properties to express properties of sets of traces, and they are increasingly popular in specifying various security and performance-related properties in domains such as cyber-physical systems, smart grids, and automotive. This paper introduces HyperTWTL, which extends Time Window Temporal Logic (TWTL)-a domain-specific formal specification language for robotics, by allowing explicit and simultaneous quantification over multiple execution traces. We propose two different semantics for HyperTWTL, synchronous and asynchronous, based on the alignment of the timestamps in the traces. Consequently, we demonstrate the application of HyperTWTL in formalizing important information-flow security policies and concurrency for robotics applications. Furthermore, we introduce a model checking algorithm for verifying fragments of HyperTWTL by reducing the problem to a TWTL model checking problem.


  • Motion Planning Using Hyperproperties for Time Window Temporal Logic

    by Ernest Bonnah, Luan Nguyen, Khaza Anuarul Hoque

    Hyperproperties are increasingly popular in verifying security policies and synthesis of control for dynamic systems. Hyperproperties generalize trace properties to enable reasoning about multiple computation traces that traditional trace properties cannot. Recent works show the effectiveness and prospect of Hyperproperties, specifically Hyperproperties for Linear Temporal Logic (HyperLTL), in optimality-, robustness-, and privacy-aware robotic motion planning. However, despite their rich expressiveness, HyperLTL cannot express tasks with time constraints. This letter presents HyperTWTL, which extends the compact semantics of Time Window Temporal Logic (TWTL) with explicit and concurrent quantification over multiple execution traces. We demonstrate that HyperTWTL can be used to formalize complex robotic planning objectives. Given HyperTWTL specifications, we also propose a symbolic approach for synthesizing optimality-, robustness-, and privacy-aware strategies by reducing the planning problem to a first-order logic satisfiability problem. The planning problem was then solved using two industrial-strength SMT solvers. The feasibility of HyperTWTL and the efficiency and scalability of the proposed strategy synthesis approach are demonstrated by formalizing important motion planning objectives of a surveillance mission case study and synthesizing the respective strategies using Z3 and CVC4 SMT solvers.


  • Decentralized Safe Control for Distributed Cyber-Physical Systems Using Real-Time Reachability Analysis

    by Luan Viet Nguyen, Hoang-Dung Tran, Taylor Johnson, Vijay Gupta

    In this paper, we present a decentralized safe control (DSC) approach for distributed cyber-physical systems based on conducting reachability analysis in real-time. Each agent can periodically compute the local reachable set from its current local time to some time instant in the near future, and then broadcast a message containing the computed reachable set to the other agents via a shared communication channel. By comparing its own reachable set to unsafe regions such as obstacles, and received reachable sets in a peer-to-peer manner, the agent can predict if any collision may exist shortly. In this circumstance, the agent can utilize the unsafe intersection of its computed reachable set, the unsafe regions and the received reachable sets to recalculate a new set of waypoints and update its corresponding control strategies. As a result, our DSC approach can ensure a distributed system achieving a mission goal with a collision-free guarantee. For evaluation, we applied the proposed DSC method to perform a decentralized control, in real-time, a group of quadcopters conducting a distributed patrol mission with safety guarantees.