Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter

No abstract is available for this paper.

• Publication year

  2021

• Venue

  Formal Aspects of Computing

• Publication date

  2021-08-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1007/s00165-021-00553-4
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Robustness Verification of Semantic Segmentation Neural Networks Using Relaxed Reachability

  2021cited by this paper
• Improved Geometric Path Enumeration for Verifying ReLU Neural Networks

  2020influential reference
• Verification of Deep Convolutional Neural Networks Using ImageStars

  2020cited by this paper
• NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems

  2020cited by this paper
• An abstract domain for certifying neural networks

  2019influential reference
• Verification of RNN-Based Neural Agent-Environment Systems

  2019cited by this paper
• Star-Based Reachability Analysis of Deep Neural Networks

  2019cited by this paper
• The Marabou Framework for Verification and Analysis of Deep Neural Networks

  2019cited by this paper
• Parallelizable Reachability Analysis Algorithms for Feed-Forward Neural Networks

  2019influential reference
• AI 2 : Safety and Robustness Certification of Neural Networks with Abstract Interpretation

  2018cited by this paper
• Formal Security Analysis of Neural Networks using Symbolic Intervals

  2018cited by this paper
• Towards Fast Computation of Certified Robustness for ReLU Networks

  2018cited by this paper
• Efficient Formal Safety Analysis of Neural Networks

  2018cited by this paper
• Verification for Machine Learning, Autonomy, and Neural Networks Survey

  2018cited by this paper
• Deep Neural Network Compression for Aircraft Collision Avoidance Systems

  2018cited by this paper
• Reachability Analysis for Neural Agent-Environment Systems

  2018cited by this paper
• Efficient Neural Network Robustness Certification with General Activation Functions

  2018cited by this paper
• Formal Verification of CNN-based Perception Systems

  2018cited by this paper
• Fast and Effective Robustness Certification

  2018cited by this paper
• Output Reachable Set Estimation and Verification for Multilayer Neural Networks

  2017cited by this paper
• Safety Verification of Deep Neural Networks ∗

  2017cited by this paper
• Output Range Analysis for Deep Neural Networks

  2017cited by this paper
• An approach to reachability analysis for feed-forward ReLU neural networks

  2017cited by this paper
• A survey on deep learning in medical image analysis

  2017cited by this paper
• Simulation-Equivalent Reachability of Large Linear Systems with Inputs

  2017cited by this paper
• Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

  2017cited by this paper
• A survey of deep neural network architectures and their applications

  2017cited by this paper
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

  2017cited by this paper
• Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

  2017cited by this paper
• End to End Learning for Self-Driving Cars

  2016cited by this paper
• Measuring Neural Net Robustness with Constraints

  2016cited by this paper
• Safety Verification of Deep Neural Networks

  2016cited by this paper
• DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks

  2015cited by this paper
• Explaining and Harnessing Adversarial Examples

  2014cited by this paper
• An Abstraction-Refinement Approach to Verification of Artificial Neural Networks

  2010cited by this paper
• The mnist database of handwritten digits

  2005cited by this paper
• Multi-Parametric Toolbox (MPT)

  2004cited by this paper

• Reachability analysis of recurrent neural networks

  2025cites this paper
• Generalizing neural network verification to the family of piece-wise linear activation functions

  2025cites this paper
• Improve Certified Training with Signal-to-Noise Ratio Loss to Decrease Neuron Variance and Increase Neuron Stability

  2024influential citation
• Towards Verification-Driven Control Learning

  2024cites this paper
• QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis

  2023cites this paper
• Reachability Analysis of Sigmoidal Neural Networks

  2023cites this paper
• Tutorial: Neural Network and Autonomous Cyber-Physical Systems Formal Verification for Trustworthy AI and Safe Autonomy

  2023cites this paper
• Empirical Analysis of Benchmark Generation for the Verification of Neural Network Image Classifiers

  2023influential citation
• Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

  2023cites this paper
• Verification of Fuzzy Decision Trees

  2023cites this paper
• Verification of Recurrent Neural Networks with Star Reachability

  2023influential citation
• A DPLL(T) Framework for Verifying Deep Neural Networks

  2023cites this paper
• Efficient Complete Verification of Neural Networks via Layerwised Splitting and Refinement

  2022cites this paper
• Reachability Set Analysis of Closed-Loop Nonlinear Systems with Neural Network Controllers

  2022cites this paper