HTHoang-Dung Tran

Hoang-Dung Tran

*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


Hoang-Dung Tran has a total of 34 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

  • Quantitative verification of learning-enabled systems using ProbStar reachability

    by Yuntao Li, Sung Woo Choi, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Hoang-Dung Tran

  • Open Access

    StarV: A Qualitative and Quantitative Verification Tool for Learning-Enabled Systems

    by Hoang-Dung Tran, Sung Woo Choi, Yuntao Li, Qing Liu, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos

    This paper presents StarV, a new tool for verifying deep neural networks (DNNs) and learning-enabled Cyber-Physical Systems (Le-CPS) using the well-known star reachability. Distinguished from existing star-based verification tools such as NNV and NNENUM and others, StarV not only offers qualitative verification techniques using Star and ImageStar reachability analysis but is also the first tool to propose using ProbStar reachability for quantitative verification of DNNs with piecewise linear activation functions and Le-CPS. Notably, it introduces a novel ProbStar Temporal Logic formalism and associated algorithms, enabling the quantitative verification of DNNs and Le-CPS’s temporal behaviors. Additionally, StarV presents a novel SparseImageStar set representation and associated reachability algorithm that allows users to verify deep convolutional neural networks and semantic segmentation networks with more memory efficiency. StarV is evaluated in comparison with state-of-the-art in many challenging benchmarks. The experiments show that StarV outperforms existing tools in many aspects, such as timing performance, scalability, and memory consumption.


  • 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.


  • Open Access

    ProbStar Temporal Logic for Verifying Complex Behaviors of Learning-enabled Systems

    by Hoang-Dung Tran, Sung Woo Choi, Yuntao Li, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos


  • Open Access

    Quantitative Verification for Neural Networks using ProbStars

    by Hoang-Dung Tran, Sungwoo Choi, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Danil Prokhorov

    Most deep neural network (DNN) verification research focuses on qualitative verification, which answers whether or not a DNN violates a safety/robustness property. This paper proposes an approach to convert qualitative verification into quantitative verification for neural networks. The resulting quantitative verification method not only can answer YES or NO questions but also can compute the probability of a property being violated. To do that, we introduce the concept of a probabilistic star (or shortly ProbStar), a new variant of the well-known star set, in which the predicate variables belong to a Gaussian distribution and propose an approach to compute the probability of a probabilistic star in high-dimensional space. Unlike existing works dealing with constrained input sets, our work considers the input set as a truncated multivariate normal (Gaussian) distribution, i.e., besides the constraints on the input variables, the input set has a probability of the constraints being satisfied. The input distribution is represented as a probabilistic star set and is propagated through a network to construct the output reachable set containing multiple ProbStars, which are used to verify the safety or robustness properties of the network. In case of a property is violated, the violation probability can be computed precisely by an exact verification algorithm or approximately by an overapproximate verification algorithm. The proposed approach is implemented in a tool named StarV and is evaluated using the well-known ACASXu networks and a rocket landing benchmark.


  • Open Access

    Verification of Recurrent Neural Networks with Star Reachability

    by Hoang Dung Tran, Sung Woo Choi, Xiaodong Yang, Tomoya Yamaguchi, Bardh Hoxha, Danil Prokhorov

    The paper extends the recent star reachability method to verify the robustness of recurrent neural networks (RNNs) for use in safety-critical applications. RNNs are a popular machine learning method for various applications, but they are vulnerable to adversarial attacks, where slightly perturbing the input sequence can lead to an unexpected result. Recent notable techniques for verifying RNNs include unrolling, and invariant inference approaches. The first method has scaling issues since unrolling an RNN creates a large feedforward neural network. The second method, using invariant sets, has better scalability but can produce unknown results due to the accumulation of overapproximation errors over time. This paper introduces a complementary verification method for RNNs that is both sound and complete. A relaxation parameter can be used to convert the method into a fast overapproximation method that still provides soundness guarantees. The method is designed to be used with NNV, a tool for verifying deep neural networks and learning-enabled cyber-physical systems. Compared to state-of-the-art methods, the extended exact reachability method is 10 × faster, and the overapproximation method is 100 × to 5000 × faster.


  • 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.