Dissertation · 2020 · Open access

On the adversarial robustness of Gaussian processes

Patane, Andrea

Oxford University Research Archive (ORA) (University of Oxford) · Published 1 January 2020 · DOI 10.5287/ora-dxxpay2za

Open PDFView at the publisherCite this paper

In brief

“On the adversarial robustness of Gaussian processes” is a 2020 dissertation by Patane, Andrea, published in Oxford University Research Archive (ORA) (University of Oxford). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at Oxford University Research Archive (ORA) (University of Oxford).

Citations
0
References
189
Authors
1

Abstract

We study the robustness of Bayesian inference with Gaussian processes (GP) under adversarial attack settings. We begin by noticing how the distinction between model prediction and decision in Bayesian settings naturally leads us to give two different notions of adversarial robustness. The former, probabilistic adversarial robustness, is concerned with the behaviour of the posterior distribution, formally characterising its worst-case attack uncertainty. On the other hand, adversarial robustness is concerned with local stability of the model decision, and is strictly correlated with bounds on the predictive posterior distribution of the model. In the first part of this thesis we show how, by relying on the Borell-TIS inequality, the computation of probabilistic adversarial robustness can be translated to the solution of a set of optimisation problems defined over the GP posterior mean, variance and specific derived quantities. In order to solve these, we develop a general framework for the lower- and upper-bounding of GP posterior parameters, which relies on interval bound propagation techniques, the computation of linear and lower upper bounding functions and the solution of linear and convex-quadratic programming problems. Employing the central limit theorem for stochastic processes, we then demonstrate how the derived bounds can also be used for the adversarial analysis of infinitely-wide deep BNN architectures. In the second part of this thesis, we show how a suitably defined discretisation of the GP latent space can be used to convert the computation of adversarial robustness to the solution of a finite number of optimisation problem over a set of uni-dimensional Gaussian integral functions. We proceed by extending and adapting the GP optimisation framework developed in the context of probabilistic robustness to the formal solution of these integrals. We rely on the theory of branch-and-bound optimisation algorithms to formally prove that our method is guaranteed to terminate in finitely-many steps to an $\epsilon$-exact solution of the problem, for any $\epsilon > 0$ selected a-priori. Furthermore, the method developed is anytime, in that it can be stopped at any point during its computation and still provide formal lower and upper bounds that can be used to certify the GP adversarial robustness. By carefully designing suitable prior functions, we then show how GPs provide us with competitive and state-of-the-art models for their application in affective computing. We finally rely on three datasets for affect recognition from physiological signals as a real-world testbed to analyse the scalability and the practical feasibility of the methods we have developed for the verification and interpretation of GP models, which we argue are crucial for the development…

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Andrea, P. (2020). On the adversarial robustness of Gaussian processes. Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-dxxpay2za

MLA 9

Andrea, Patane,. “On the adversarial robustness of Gaussian processes.” Oxford University Research Archive (ORA) (University of Oxford), 2020. https://doi.org/10.5287/ora-dxxpay2za.

Chicago

Andrea, Patane,. 2020. “On the adversarial robustness of Gaussian processes.” Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-dxxpay2za.

Harvard

Andrea, P. (2020) ‘On the adversarial robustness of Gaussian processes’, Oxford University Research Archive (ORA) (University of Oxford). doi:10.5287/ora-dxxpay2za.

IEEE

P. Andrea, “On the adversarial robustness of Gaussian processes,” Oxford University Research Archive (ORA) (University of Oxford), 2020, doi: 10.5287/ora-dxxpay2za.

BibTeX

@phdthesis{andrea2020adversarial,
  title     = {{On the adversarial robustness of Gaussian processes}},
  author    = {Andrea, Patane,},
  year      = {2020},
  doi       = {10.5287/ora-dxxpay2za},
  url       = {https://doi.org/10.5287/ora-dxxpay2za}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • adversarial robustness
  • Gaussian processes
  • probabilistic robustness
  • Bayesian inference
  • branch and bound
  • affective computing
  • affect recognition
  • physiological signals

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Andrea, P. (2020). On the adversarial robustness of Gaussian processes. Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-dxxpay2za

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Oxford University Research Archive (ORA) (University of Oxford): sign in and open the PDF from this page.

Who wrote this paper?

Patane, Andrea.

What is the DOI of this paper?

10.5287/ora-dxxpay2za, permanently at https://doi.org/10.5287/ora-dxxpay2za. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.