Skip to main content

and
Your search also matched 9 preview-only Content is preview-only when you or your institution have not yet subscribed to it.

By making our abstracts and previews universally accessible we help you purchase only the content that is relevant to you.
results, e.g.

An overview of structural coverage metrics for testing neural networks

Include preview-only content
  1. Chapter and Conference Paper

    Correction to: Rule-Based Runtime Mitigation Against Poison Attacks on Neural Networks

    In an older version of this paper, there was error in the figure 3, (e) and (f) was incorrect. This has been corrected.

    Muhammad Usman, Divya Gopinath, Youcheng Sun, Corina S. Păsăreanu in Runtime Verification (2022)

  2. Chapter and Conference Paper

    NNrepair: Constraint-Based Repair of Neural Network Classifiers

    We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fa...

    Muhammad Usman, Divya Gopinath, Youcheng Sun, Yannic Noller in Computer Aided Verification (2021)

  3. Chapter and Conference Paper

    Building Better Bit-Blasting for Floating-Point Problems

    An effective approach to handling the theory of floating-point is to reduce it to the theory of bit-vectors. Implementing the required encodings is complex, error prone and requires a deep understanding of flo...

    Martin Brain, Florian Schanda, Youcheng Sun in Tools and Algorithms for the Construction … (2019)

  4. Chapter and Conference Paper

    Optimising Spectrum Based Fault Localisation for Single Fault Programs Using Specifications

    Spectrum based fault localisation determines how suspicious a line of code is with respect to being faulty as a function of a given test suite. Outstanding problems include identifying properties that the test...

    David Landsberg, Youcheng Sun in Fundamental Approaches to Software Enginee… (2018)