Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 13 of 13 for “"Network Verification"”.

  1. Foundations for practical network verification

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms

    uiuc Repository record for Foundations for practical network verification (opens in a new tab)

  2. Order-Leading Branch and Bound for Neural Network Verification

    … robustness, and safety of deep neural networks has become a pressing imperative. Despite their ubiquitous deployment in image classification, software engineering, and bug detection, the field still lacks rigorous methodologies to verify their behavior. Although high-level principles …

    unsw Repository record for Order-Leading Branch and Bound for Neural Network Verification (opens in a new tab)

  3. SDP-CROWN: Efficient bound propagation for neural network verification with tightness of semidefinite programming

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for SDP-CROWN: Efficient bound propagation for neural network verification with tightness of semidefinite programming (opens in a new tab)

  4. A linear constraint driven approach to efficiently enhancing branch and bound in neural network verification

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for A linear constraint driven approach to efficiently enhancing branch and bound in neural network verification (opens in a new tab)

  5. Practical verification of network planes

    Formal network verification is a rapidly advancing field of research, encompassing a wide array of verticals such as data plane verification, configuration verification, network software verification etc. More and more real-world networks are deploying network verification as a tool to prevent …

    uiuc Repository record for Practical verification of network planes (opens in a new tab)

  6. Provably reliable machine learning systems

    … systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, …

    uiuc Repository record for Provably reliable machine learning systems (opens in a new tab)

  7. Toward improved tropical cyclone intensity forecasts : probabilistic prediction, predictability, and the role of verification

    … scored poorly in mean absolute error (MAE) verification, despite the concurrent advancement of TC modeling and observing capabilities. Given the importance of understanding this situation for the future of TC intensity prediction, the "TC intensity prediction problem" is examined here on two …

    mit Repository record for Toward improved tropical cyclone intensity forecasts : probabilistic prediction, predictability, and the role of verification (opens in a new tab)

  8. Neural network based method for solving SMT problems

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for Neural network based method for solving SMT problems (opens in a new tab)

  9. Network analysis, inference and verification

    Securely operating large-scale networks is a non-trivial task involving interactions between various hardware devices, protocols, and configurations, all of which need to work in tandem for the network to be secure and in the desired state that the network administrators want it to be in. …

    uiuc Repository record for Network analysis, inference and verification (opens in a new tab)

  10. A formal semantics of P4 and applications

    … combined with the complexity of devices and networks, increases the chance of introducing subtle bugs that are hard to discover manually. Worse, this is a domain where bugs can have catastrophic consequences, yet formal analysis tools for P4 programs and networks are missing. We argue that …

    uiuc Repository record for A formal semantics of P4 and applications (opens in a new tab)

  11. Anomaly detection using network metadata

    Networks are traditionally configured manually by operators who can potentially introduce misconfigurations, exposing the network to security risks. Furthermore, as network complexity grows it becomes harder to track anomalous activity in networks, especially for configuration changes which may go …

    uiuc Repository record for Anomaly detection using network metadata (opens in a new tab)

  12. Towards Reliable AI via Efficient Verification of Binarized Neural Networks

    Deep neural networks have achieved great success on many tasks and even surpass human performance in certain settings. Despite this success, neural networks are known to be vulnerable to the problem of adversarial inputs, where small and human- imperceptible changes in the input cause large and …

    mit Repository record for Towards Reliable AI via Efficient Verification of Binarized Neural Networks (opens in a new tab)

  13. Scalable verification for complex networks

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms

    uiuc Repository record for Scalable verification for complex networks (opens in a new tab)