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 …
Sok: Certified robustness for deep neural networks
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …
When to trust AI: advances and challenges for certification of neural networks
M Kwiatkowska, X Zhang - 2023 18th Conference on Computer …, 2023 - ieeexplore.ieee.org
Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for
deployment in a wide range of applications, such as autonomous systems, medical …
deployment in a wide range of applications, such as autonomous systems, medical …
Detecting violations of differential privacy for quantum algorithms
Quantum algorithms for solving a wide range of practical problems have been proposed in
the last ten years, such as data search and analysis, product recommendation, and credit …
the last ten years, such as data search and analysis, product recommendation, and credit …
[PDF][PDF] Formally Explaining Neural Networks within Reactive Systems
Deep neural networks (DNNs) are increasingly being used as controllers in reactive
systems. However, DNNs are highly opaque, which renders it difficult to explain and justify …
systems. However, DNNs are highly opaque, which renders it difficult to explain and justify …
Double sampling randomized smoothing
Neural networks (NNs) are known to be vulnerable against adversarial perturbations, and
thus there is a line of work aiming to provide robustness certification for NNs, such as …
thus there is a line of work aiming to provide robustness certification for NNs, such as …
Cc: Causality-aware coverage criterion for deep neural networks
Deep neural network (DNN) testing approaches have grown fast in recent years to test the
correctness and robustness of DNNs. In particular, DNN coverage criteria are frequently …
correctness and robustness of DNNs. In particular, DNN coverage criteria are frequently …
A quantitative geometric approach to neural-network smoothness
Fast and precise Lipschitz constant estimation of neural networks is an important task for
deep learning. Researchers have recently found an intrinsic trade-off between the accuracy …
deep learning. Researchers have recently found an intrinsic trade-off between the accuracy …
A general construction for abstract interpretation of higher-order automatic differentiation
We present a novel, general construction to abstractly interpret higher-order automatic
differentiation (AD). Our construction allows one to instantiate an abstract interpreter for …
differentiation (AD). Our construction allows one to instantiate an abstract interpreter for …
Certifying robustness to programmable data bias in decision trees
A Meyer, A Albarghouthi… - Advances in Neural …, 2021 - proceedings.neurips.cc
Datasets can be biased due to societal inequities, human biases, under-representation of
minorities, etc. Our goal is to certify that models produced by a learning algorithm are …
minorities, etc. Our goal is to certify that models produced by a learning algorithm are …