Algorithms for verifying deep neural networks
Deep neural networks are widely used for nonlinear function approximation, with
applications ranging from computer vision to control. Although these networks involve the …
applications ranging from computer vision to control. Although these networks involve the …
Deep reinforcement learning verification: a survey
Deep reinforcement learning (DRL) has proven capable of superhuman performance on
many complex tasks. To achieve this success, DRL algorithms train a decision-making agent …
many complex tasks. To achieve this success, DRL algorithms train a decision-making agent …
Trustllm: Trustworthiness in large language models
Large language models (LLMs), exemplified by ChatGPT, have gained considerable
attention for their excellent natural language processing capabilities. Nonetheless, these …
attention for their excellent natural language processing capabilities. Nonetheless, these …
General cutting planes for bound-propagation-based neural network verification
Bound propagation methods, when combined with branch and bound, are among the most
effective methods to formally verify properties of deep neural networks such as correctness …
effective methods to formally verify properties of deep neural networks such as correctness …
Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification
Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …
efficient and can significantly accelerate branch-and-bound (BaB) based complete …
Are formal methods applicable to machine learning and artificial intelligence?
Formal approaches can provide strict correctness guarantees for the development of both
hardware and software systems. In this work, we examine state-of-the-art formal methods for …
hardware and software systems. In this work, we examine state-of-the-art formal methods for …
Robust deep reinforcement learning against adversarial perturbations on state observations
A deep reinforcement learning (DRL) agent observes its states through observations, which
may contain natural measurement errors or adversarial noises. Since the observations …
may contain natural measurement errors or adversarial noises. Since the observations …
Collaboration challenges in building ml-enabled systems: Communication, documentation, engineering, and process
The introduction of machine learning (ML) components in software projects has created the
need for software engineers to collaborate with data scientists and other specialists. While …
need for software engineers to collaborate with data scientists and other specialists. While …
NNV: the neural network verification tool for deep neural networks and learning-enabled cyber-physical systems
This paper presents the Neural Network Verification (NNV) software tool, a set-based
verification framework for deep neural networks (DNNs) and learning-enabled cyber …
verification framework for deep neural networks (DNNs) and learning-enabled cyber …
First three years of the international verification of neural networks competition (VNN-COMP)
This paper presents a summary and meta-analysis of the first three iterations of the annual
International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021 …
International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021 …