186 citations · 440 across the 14 of their papers we have counts for
16 papers
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Haoze Wu, Omri Isac, Aleksandar Zeljić +14
This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design a…
Generating Probabilistic Safety Guarantees for Neural Network Controllers
Sydney M. Katz, Kyle D. Julian, Christopher A. Strong +1
Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, howeve…
Global Optimization of Objective Functions Represented by ReLU Networks
Christopher A. Strong, Haoze Wu, Aleksandar Zeljić +4
Neural networks can learn complex, non-convex functions, and it is challenging to guarantee their correct behavior in safety-critical contexts. Many approaches exist to find failur…
Parallelization Techniques for Verifying Neural Networks
Haoze Wu, Alex Ozdemir, Aleksandar Zeljić +7
Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parall…
Validation of Image-Based Neural Network Controllers through Adaptive Stress Testing
Kyle D. Julian, Ritchie Lee, Mykel J. Kochenderfer
Neural networks have become state-of-the-art for computer vision problems because of their ability to efficiently model complex functions from large amounts of data. While neural n…
Guaranteeing Safety for Neural Network-Based Aircraft Collision Avoidance Systems
Kyle D. Julian, Mykel J. Kochenderfer
The decision logic for the ACAS X family of aircraft collision avoidance systems is represented as a large numeric table. Due to storage constraints of certified avionics hardware,…
Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regions
Kyle D. Julian, Shivam Sharma, Jean-Baptiste Jeannin +1
The next generation of aircraft collision avoidance systems frame the problem as a Markov decision process and use dynamic programming to optimize the alerting logic. The resulting…
A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllers
Kyle D. Julian, Mykel J. Kochenderfer
Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to gua…
Visual Depth Mapping from Monocular Images using Recurrent Convolutional Neural Networks
John Mern, Kyle Julian, Rachael E. Tompa +1
A reliable sense-and-avoid system is critical to enabling safe autonomous operation of unmanned aircraft. Existing sense-and-avoid methods often require specialized sensors that ar…
Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning
Kyle D. Julian, Mykel J. Kochenderfer
Teams of autonomous unmanned aircraft can be used to monitor wildfires, enabling firefighters to make informed decisions. However, controlling multiple autonomous fixed-wing aircra…
Deep Neural Network Compression for Aircraft Collision Avoidance Systems
Kyle D. Julian, Mykel J. Kochenderfer, Michael P. Owen
One approach to designing decision making logic for an aircraft collision avoidance system frames the problem as a Markov decision process and optimizes the system using dynamic pr…
Image-based Guidance of Autonomous Aircraft for Wildfire Surveillance and Prediction
Kyle D. Julian, Mykel J. Kochenderfer
Small unmanned aircraft can help firefighters combat wildfires by providing real-time surveillance of the growing fires. However, guiding the aircraft autonomously given only wildf…
Toward Scalable Verification for Safety-Critical Deep Networks
Lindsey Kuper, Guy Katz, Justin Gottschlich +3
The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Form…
Decomposition Methods with Deep Corrections for Reinforcement Learning
Maxime Bouton, Kyle Julian, Alireza Nakhaei +2
Decomposition methods have been proposed to approximate solutions to large sequential decision making problems. In contexts where an agent interacts with multiple entities, utility…
Towards Proving the Adversarial Robustness of Deep Neural Networks
Guy Katz, Clark Barrett, David L. Dill +2
Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficul…
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Guy Katz, Clark Barrett, David Dill +2
Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical syst…