Adversarial robustness guarantees for classification with Gaussian Processes

Adversarial robustness guarantees for classification with Gaussian Processes

We investigate adversarial robustness of Gaussian Process classification (GPC) models. Specifically, given a compact subset of the input space T⊆ℝd enclosing a test point x∗ and a GPC trained on a dataset , we aim to compute the minimum and the maximum classification probability for the GPC over al...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй
Үндсэн зохиолчид:	Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S
Формат:	Conference item
Хэл сонгох:	English
Хэвлэсэн:	Proceedings of Machine Learning Research 2020

Ижил төстэй зүйлс

Adversarial robustness guarantees for Gaussian processes
-н: Patane, A, зэрэг
Хэвлэсэн: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2019)

Safety guarantees for iterative predictions with Gaussian Processes
-н: Polymenakos, K, зэрэг
Хэвлэсэн: (2021)

Statistical guarantees for the robustness of Bayesian neural networks
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2019)

On the adversarial robustness of Gaussian processes
-н: Patanè, A
Хэвлэсэн: (2020)

Adversarial robustness certification for Bayesian neural networks
-н: Wicker, M, зэрэг
Хэвлэсэн: (2024)

Bayesian inference with certifiable adversarial robustness
-н: Wicker, M, зэрэг
Хэвлэсэн: (2021)

Individual fairness guarantees for neural networks
-н: Benussi, E, зэрэг
Хэвлэсэн: (2022)

Adversarially robust optimization with Gaussian processes
-н: Bogunovic, I, зэрэг
Хэвлэсэн: (2021)

Adversarially robust optimization with Gaussian processes
-н: Bogunovic, Ilija, зэрэг
Хэвлэсэн: (2022)

Gaussian processes with physiologically-inspired priors for physical arousal recognition
-н: Ghiasi, S, зэрэг
Хэвлэсэн: (2020)

Physiologically-informed Gaussian processes for interpretable modelling of psycho-physiological states
-н: Ghiasi, S, зэрэг
Хэвлэсэн: (2022)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
-н: Michelmore, R, зэрэг
Хэвлэсэн: (2020)

On the adversarial robustness of Bayesian machine learning models
-н: Blaas, AC
Хэвлэсэн: (2021)

Adversarial Robustness Guarantees for Random Deep Neural Networks
-н: De Palma, Giacomo, зэрэг
Хэвлэсэн: (2022)

Robust optimization for adversarial learning with finite sample complexity guarantees
-н: Bertolace, A, зэрэг
Хэвлэсэн: (2024)

Robustness guarantees for deep neural networks on videos
-н: Kwiatkowska, M, зэрэг
Хэвлэсэн: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
-н: Kwiatkowska, M
Хэвлэсэн: (2019)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
-н: Kwiatkowska, M
Хэвлэсэн: (2020)

Provable guarantees on the robustness of decision rules to causal interventions
-н: Wang, B, зэрэг
Хэвлэсэн: (2021)

Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
-н: Benjamin Appiah, зэрэг
Хэвлэсэн: (2020-01-01)

On guaranteed optimal robust explanations for NLP models
-н: La Malfa, E, зэрэг
Хэвлэсэн: (2021)

Robustness of 3D deep learning in an adversarial setting
-н: Wicker, M, зэрэг
Хэвлэсэн: (2020)

Formal and efficient synthesis for continuous-time linear stochastic hybrid processes
-н: Laurenti, L, зэрэг
Хэвлэсэн: (2020)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
-н: Kwiatkowska, M
Хэвлэсэн: (2022)

A language for modeling and optimizing experimental biological protocols
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2021)

A Stochastic Hybrid Approximation for Chemical Kinetics Based on the Linear Noise Approximation
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2016)

Programming discrete distributions with chemical reaction networks
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2017)

Programming discrete distributions with chemical reaction networks
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2016)

Stochastic analysis of chemical reaction networks using linear noise approximation
-н: Cardelli, L, зэрэг
Хэвлэсэн: (2016)

Scalable Gaussian process inference with finite-data mean and variance guarantees
-н: Huggins, Jonathan H., зэрэг
Хэвлэсэн: (2020)

Assessing robustness of text classification through maximal safe radius computation
-н: La Malfa, E, зэрэг
Хэвлэсэн: (2020)

Adversarial attacks on graph classification via Bayesian optimisation
-н: Wan, X, зэрэг
Хэвлэсэн: (2021)

Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
-н: Desheng Wang, зэрэг
Хэвлэсэн: (2023-03-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
-н: Wijk, H, зэрэг
Хэвлэсэн: (2022)

Probabilistic safety for bayesian neural networks
-н: Wicker, M, зэрэг
Хэвлэсэн: (2020)

Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
-н: Arslan Ali, зэрэг
Хэвлэсэн: (2023-03-01)

Central limit model checking
-н: Bortolussi, L, зэрэг
Хэвлэсэн: (2019)

Approximation of probabilistic reachability for chemical reaction networks using the linear noise approximation
-н: Kwiatkowska, M, зэрэг
Хэвлэсэн: (2016)

Central limit model checking
-н: Bortolussi, L, зэрэг
Хэвлэсэн: (2018)