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...

Szczegółowa specyfikacja

Opis bibliograficzny
Główni autorzy:	Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S
Format:	Conference item
Język:	English
Wydane:	Proceedings of Machine Learning Research 2020

Podobne zapisy

Adversarial robustness guarantees for Gaussian processes
od: Patane, A, i wsp.
Wydane: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
od: Cardelli, L, i wsp.
Wydane: (2019)

Safety guarantees for iterative predictions with Gaussian Processes
od: Polymenakos, K, i wsp.
Wydane: (2021)

Statistical guarantees for the robustness of Bayesian neural networks
od: Cardelli, L, i wsp.
Wydane: (2019)

On the adversarial robustness of Gaussian processes
od: Patanè, A
Wydane: (2020)

Adversarial robustness certification for Bayesian neural networks
od: Wicker, M, i wsp.
Wydane: (2024)

Bayesian inference with certifiable adversarial robustness
od: Wicker, M, i wsp.
Wydane: (2021)

Individual fairness guarantees for neural networks
od: Benussi, E, i wsp.
Wydane: (2022)

Adversarially robust optimization with Gaussian processes
od: Bogunovic, I, i wsp.
Wydane: (2021)

Adversarially robust optimization with Gaussian processes
od: Bogunovic, Ilija, i wsp.
Wydane: (2022)

Gaussian processes with physiologically-inspired priors for physical arousal recognition
od: Ghiasi, S, i wsp.
Wydane: (2020)

Physiologically-informed Gaussian processes for interpretable modelling of psycho-physiological states
od: Ghiasi, S, i wsp.
Wydane: (2022)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
od: Michelmore, R, i wsp.
Wydane: (2020)

On the adversarial robustness of Bayesian machine learning models
od: Blaas, AC
Wydane: (2021)

Adversarial Robustness Guarantees for Random Deep Neural Networks
od: De Palma, Giacomo, i wsp.
Wydane: (2022)

Robust optimization for adversarial learning with finite sample complexity guarantees
od: Bertolace, A, i wsp.
Wydane: (2024)

Robustness guarantees for deep neural networks on videos
od: Kwiatkowska, M, i wsp.
Wydane: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
od: Kwiatkowska, M
Wydane: (2019)

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

Provable guarantees on the robustness of decision rules to causal interventions
od: Wang, B, i wsp.
Wydane: (2021)

Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
od: Benjamin Appiah, i wsp.
Wydane: (2020-01-01)

On guaranteed optimal robust explanations for NLP models
od: La Malfa, E, i wsp.
Wydane: (2021)

Robustness of 3D deep learning in an adversarial setting
od: Wicker, M, i wsp.
Wydane: (2020)

Formal and efficient synthesis for continuous-time linear stochastic hybrid processes
od: Laurenti, L, i wsp.
Wydane: (2020)

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

A language for modeling and optimizing experimental biological protocols
od: Cardelli, L, i wsp.
Wydane: (2021)

A Stochastic Hybrid Approximation for Chemical Kinetics Based on the Linear Noise Approximation
od: Cardelli, L, i wsp.
Wydane: (2016)

Programming discrete distributions with chemical reaction networks
od: Cardelli, L, i wsp.
Wydane: (2017)

Programming discrete distributions with chemical reaction networks
od: Cardelli, L, i wsp.
Wydane: (2016)

Stochastic analysis of chemical reaction networks using linear noise approximation
od: Cardelli, L, i wsp.
Wydane: (2016)

Scalable Gaussian process inference with finite-data mean and variance guarantees
od: Huggins, Jonathan H., i wsp.
Wydane: (2020)

Assessing robustness of text classification through maximal safe radius computation
od: La Malfa, E, i wsp.
Wydane: (2020)

Adversarial attacks on graph classification via Bayesian optimisation
od: Wan, X, i wsp.
Wydane: (2021)

Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
od: Desheng Wang, i wsp.
Wydane: (2023-03-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
od: Wijk, H, i wsp.
Wydane: (2022)

Probabilistic safety for bayesian neural networks
od: Wicker, M, i wsp.
Wydane: (2020)

Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
od: Arslan Ali, i wsp.
Wydane: (2023-03-01)

Central limit model checking
od: Bortolussi, L, i wsp.
Wydane: (2019)

Approximation of probabilistic reachability for chemical reaction networks using the linear noise approximation
od: Kwiatkowska, M, i wsp.
Wydane: (2016)

Central limit model checking
od: Bortolussi, L, i wsp.
Wydane: (2018)