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...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S
Formáid:	Conference item
Teanga:	English
Foilsithe / Cruthaithe:	Proceedings of Machine Learning Research 2020

Míreanna comhchosúla

Adversarial robustness guarantees for Gaussian processes
de réir: Patane, A, et al.
Foilsithe / Cruthaithe: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2019)

Safety guarantees for iterative predictions with Gaussian Processes
de réir: Polymenakos, K, et al.
Foilsithe / Cruthaithe: (2021)

Statistical guarantees for the robustness of Bayesian neural networks
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2019)

On the adversarial robustness of Gaussian processes
de réir: Patanè, A
Foilsithe / Cruthaithe: (2020)

Adversarial robustness certification for Bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2024)

Bayesian inference with certifiable adversarial robustness
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2021)

Individual fairness guarantees for neural networks
de réir: Benussi, E, et al.
Foilsithe / Cruthaithe: (2022)

Adversarially robust optimization with Gaussian processes
de réir: Bogunovic, I, et al.
Foilsithe / Cruthaithe: (2021)

Adversarially robust optimization with Gaussian processes
de réir: Bogunovic, Ilija, et al.
Foilsithe / Cruthaithe: (2022)

Gaussian processes with physiologically-inspired priors for physical arousal recognition
de réir: Ghiasi, S, et al.
Foilsithe / Cruthaithe: (2020)

Physiologically-informed Gaussian processes for interpretable modelling of psycho-physiological states
de réir: Ghiasi, S, et al.
Foilsithe / Cruthaithe: (2022)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
de réir: Michelmore, R, et al.
Foilsithe / Cruthaithe: (2020)

On the adversarial robustness of Bayesian machine learning models
de réir: Blaas, AC
Foilsithe / Cruthaithe: (2021)

Adversarial Robustness Guarantees for Random Deep Neural Networks
de réir: De Palma, Giacomo, et al.
Foilsithe / Cruthaithe: (2022)

Robust optimization for adversarial learning with finite sample complexity guarantees
de réir: Bertolace, A, et al.
Foilsithe / Cruthaithe: (2024)

Robustness guarantees for deep neural networks on videos
de réir: Kwiatkowska, M, et al.
Foilsithe / Cruthaithe: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2019)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2020)

Provable guarantees on the robustness of decision rules to causal interventions
de réir: Wang, B, et al.
Foilsithe / Cruthaithe: (2021)

Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
de réir: Benjamin Appiah, et al.
Foilsithe / Cruthaithe: (2020-01-01)

On guaranteed optimal robust explanations for NLP models
de réir: La Malfa, E, et al.
Foilsithe / Cruthaithe: (2021)

Robustness of 3D deep learning in an adversarial setting
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2020)

Formal and efficient synthesis for continuous-time linear stochastic hybrid processes
de réir: Laurenti, L, et al.
Foilsithe / Cruthaithe: (2020)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2022)

A language for modeling and optimizing experimental biological protocols
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2021)

A Stochastic Hybrid Approximation for Chemical Kinetics Based on the Linear Noise Approximation
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2016)

Programming discrete distributions with chemical reaction networks
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2017)

Programming discrete distributions with chemical reaction networks
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2016)

Stochastic analysis of chemical reaction networks using linear noise approximation
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2016)

Scalable Gaussian process inference with finite-data mean and variance guarantees
de réir: Huggins, Jonathan H., et al.
Foilsithe / Cruthaithe: (2020)

Assessing robustness of text classification through maximal safe radius computation
de réir: La Malfa, E, et al.
Foilsithe / Cruthaithe: (2020)

Adversarial attacks on graph classification via Bayesian optimisation
de réir: Wan, X, et al.
Foilsithe / Cruthaithe: (2021)

Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
de réir: Desheng Wang, et al.
Foilsithe / Cruthaithe: (2023-03-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
de réir: Wijk, H, et al.
Foilsithe / Cruthaithe: (2022)

Probabilistic safety for bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2020)

Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
de réir: Arslan Ali, et al.
Foilsithe / Cruthaithe: (2023-03-01)

Central limit model checking
de réir: Bortolussi, L, et al.
Foilsithe / Cruthaithe: (2019)

Approximation of probabilistic reachability for chemical reaction networks using the linear noise approximation
de réir: Kwiatkowska, M, et al.
Foilsithe / Cruthaithe: (2016)

Central limit model checking
de réir: Bortolussi, L, et al.
Foilsithe / Cruthaithe: (2018)