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...

書誌詳細
主要な著者:	Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S
フォーマット:	Conference item
言語:	English
出版事項:	Proceedings of Machine Learning Research 2020

類似資料

Adversarial robustness guarantees for Gaussian processes
著者:: Patane, A, 等
出版事項: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
著者:: Cardelli, L, 等
出版事項: (2019)

Safety guarantees for iterative predictions with Gaussian Processes
著者:: Polymenakos, K, 等
出版事項: (2021)

Statistical guarantees for the robustness of Bayesian neural networks
著者:: Cardelli, L, 等
出版事項: (2019)

On the adversarial robustness of Gaussian processes
著者:: Patanè, A
出版事項: (2020)

Adversarial robustness certification for Bayesian neural networks
著者:: Wicker, M, 等
出版事項: (2024)

Bayesian inference with certifiable adversarial robustness
著者:: Wicker, M, 等
出版事項: (2021)

Individual fairness guarantees for neural networks
著者:: Benussi, E, 等
出版事項: (2022)

Adversarially robust optimization with Gaussian processes
著者:: Bogunovic, I, 等
出版事項: (2021)

Adversarially robust optimization with Gaussian processes
著者:: Bogunovic, Ilija, 等
出版事項: (2022)

Gaussian processes with physiologically-inspired priors for physical arousal recognition
著者:: Ghiasi, S, 等
出版事項: (2020)

Physiologically-informed Gaussian processes for interpretable modelling of psycho-physiological states
著者:: Ghiasi, S, 等
出版事項: (2022)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
著者:: Michelmore, R, 等
出版事項: (2020)

On the adversarial robustness of Bayesian machine learning models
著者:: Blaas, AC
出版事項: (2021)

Adversarial Robustness Guarantees for Random Deep Neural Networks
著者:: De Palma, Giacomo, 等
出版事項: (2022)

Robust optimization for adversarial learning with finite sample complexity guarantees
著者:: Bertolace, A, 等
出版事項: (2024)

Robustness guarantees for deep neural networks on videos
著者:: Kwiatkowska, M, 等
出版事項: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
著者:: Kwiatkowska, M
出版事項: (2019)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
著者:: Kwiatkowska, M
出版事項: (2020)

Provable guarantees on the robustness of decision rules to causal interventions
著者:: Wang, B, 等
出版事項: (2021)

Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
著者:: Benjamin Appiah, 等
出版事項: (2020-01-01)

On guaranteed optimal robust explanations for NLP models
著者:: La Malfa, E, 等
出版事項: (2021)

Robustness of 3D deep learning in an adversarial setting
著者:: Wicker, M, 等
出版事項: (2020)

Formal and efficient synthesis for continuous-time linear stochastic hybrid processes
著者:: Laurenti, L, 等
出版事項: (2020)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
著者:: Kwiatkowska, M
出版事項: (2022)

A language for modeling and optimizing experimental biological protocols
著者:: Cardelli, L, 等
出版事項: (2021)

A Stochastic Hybrid Approximation for Chemical Kinetics Based on the Linear Noise Approximation
著者:: Cardelli, L, 等
出版事項: (2016)

Programming discrete distributions with chemical reaction networks
著者:: Cardelli, L, 等
出版事項: (2017)

Programming discrete distributions with chemical reaction networks
著者:: Cardelli, L, 等
出版事項: (2016)

Stochastic analysis of chemical reaction networks using linear noise approximation
著者:: Cardelli, L, 等
出版事項: (2016)

Scalable Gaussian process inference with finite-data mean and variance guarantees
著者:: Huggins, Jonathan H., 等
出版事項: (2020)

Assessing robustness of text classification through maximal safe radius computation
著者:: La Malfa, E, 等
出版事項: (2020)

Adversarial attacks on graph classification via Bayesian optimisation
著者:: Wan, X, 等
出版事項: (2021)

Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
著者:: Desheng Wang, 等
出版事項: (2023-03-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
著者:: Wijk, H, 等
出版事項: (2022)

Probabilistic safety for bayesian neural networks
著者:: Wicker, M, 等
出版事項: (2020)

Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
著者:: Arslan Ali, 等
出版事項: (2023-03-01)

Central limit model checking
著者:: Bortolussi, L, 等
出版事項: (2019)

Approximation of probabilistic reachability for chemical reaction networks using the linear noise approximation
著者:: Kwiatkowska, M, 等
出版事項: (2016)

Central limit model checking
著者:: Bortolussi, L, 等
出版事項: (2018)