Skip to search formSkip to main contentSkip to account menu

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

Results show that the novel, scalable, and efficient technique presented can successfully prove properties of networks that are an order of magnitude larger than the largest networks verified using existing methods.
View PDF on arXiv (opens in a new tab)

The Marabou Framework for Verification and Analysis of Deep Neural Networks

Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems, and it performs high-level reasoning on the network that can curtail the search space and improve performance.
View via Publisher (opens in a new tab)

Policy compression for aircraft collision avoidance systems

A deep neural network is used to learn a complex non-linear function approximation of the lookup table, which reduces the required storage space by a factor of 1000 and surpasses the original table on the performance metrics and encounter sets evaluated here.
View on IEEE (opens in a new tab)

Deep Neural Network Compression for Aircraft Collision Avoidance Systems

A deep neural network is used to approximate the table, reducing the required storage space by a factor of 1000 and enabling the collision avoidance system to operate using current avionics systems.
View PDF on arXiv (opens in a new tab)

Guaranteeing Safety for Neural Network-Based Aircraft Collision Avoidance Systems

A method to provide safety guarantees when using a neural network collision avoidance system is proposed and experiments with systems inspired by ACAS X show that neural networks giving either horizontal or vertical maneuvers can be proven safe.
View on IEEE (opens in a new tab)

Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning

Teams of autonomous unmanned aircraft can be used to monitor wildfires, enabling firefighters to make informed decisions. However, controlling multiple autonomous fixed-wing aircraft to maximize fo...
View PDF on arXiv (opens in a new tab)

Towards Proving the Adversarial Robustness of Deep Neural Networks

This paper focuses on proving the adversarial robustness of deep neural networks, i.e. proving that small perturbations to a correctly-classified input to the network cannot cause it to be misclassified.
View PDF on arXiv (opens in a new tab)

Reachability Analysis for Neural Network Aircraft Collision Avoidance Systems

This research presents a novel approaches to solving sequential decision-making problems as Markov decision processes by automating the very labor-intensive and therefore time-heavy process of solving value iteration problems.
View via Publisher (opens in a new tab)

Neural Network Guidance for UAVs

View via Publisher (opens in a new tab)

A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllers

This work presents a general approach for providing guarantees for deep neural network controllers over multiple time steps using a combination of reachability methods and open source neural network verification tools.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)