Giovanni Cherubin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Giovanni Cherubin has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Adrian Weller
Department of Engineering, University of Cambridge, Cambridge, UK
1 shared publication - Alexander Gammerman
Alexander Gammerman is professor of computer science at the Centre for Reliable Machine Learning, Royal Holloway, University of London, UK
1 shared publication - Carmela Troncoso
SPRING Lab, EPFL, Lausanne, Switzerland
1 shared publication - Catuscia Palamidessi
INRIA École Polytechnique Palaiseau France
1 shared publication Davide Papini
Royal Holloway University of London
1 shared publicationIlia Nouretdinov
Royal Holloway University of London
1 shared publication
Latest Publications
- Open Access
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 388-406
Bayes Security: A Not So Average Metric
Security system designers favor worst-case security metrics, such as those derived from differential privacy (DP), due to the strong guarantees they provide. On the downside, these guarantees result in a high penalty on the system's performance. In this paper, we study Bayes security, a security metric inspired by the cryptographic advantage. Similarly to DP, Bayes security i) is independent of an adversary's prior knowledge, ii) it captures the worst-case scenario for the two most vulnerable secrets (e.g., data records); and iii) it is easy to compose, facilitating security analyses. Additionally, Bayes security iv) can be consistently estimated in a black-box manner, contrary to DP, which is useful when a formal analysis is not feasible; and v) provides a better utility-security trade-off in high-security regimes because it quantifies the risk for a specific threat model as opposed to threat-agnostic metrics such as DP. We formulate a theory around Bayes security, and we provide a thorough comparison with respect to well-known metrics, identifying the scenarios where Bayes Security is advantageous for designers.
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 388-406
Open AccessBayes Security: A Not So Average Metric
Security system designers favor worst-case security metrics, such as those derived from differential privacy (DP), due to the strong guarantees they provide. On the downside, these guarantees result in a high penalty on the system's performance. In this paper, we study Bayes security, a security metric inspired by the cryptographic advantage. Similarly to DP, Bayes security i) is independent of an adversary's prior knowledge, ii) it captures the worst-case scenario for the two most vulnerable secrets (e.g., data records); and iii) it is easy to compose, facilitating security analyses. Additionally, Bayes security iv) can be consistently estimated in a black-box manner, contrary to DP, which is useful when a formal analysis is not feasible; and v) provides a better utility-security trade-off in high-security regimes because it quantifies the risk for a specific threat model as opposed to threat-agnostic metrics such as DP. We formulate a theory around Bayes security, and we provide a thorough comparison with respect to well-known metrics, identifying the scenarios where Bayes Security is advantageous for designers.
- Open Access
Approximating Full Conformal Prediction at Scale via Influence Functions
Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP guarantees that the error rate is at most $\varepsilon$, irrespective of whether the underlying model is misspecified. However, the prohibitive computational costs of "full" CP led researchers to design scalable alternatives, which alas do not attain the same guarantees or statistical power of full CP. In this paper, we use influence functions to efficiently approximate full CP. We prove that our method is a consistent approximation of full CP, and empirically show that the approximation error becomes smaller as the training set increases; e.g., for $10^{3}$ training points the two methods output p-values that are $<10^{-3}$ apart: a negligible error for any practical application. Our methods enable scaling full CP to large real-world datasets. We compare our full CP approximation (ACP) to mainstream CP alternatives, and observe that our method is computationally competitive whilst enjoying the statistical predictive power of full CP.Open AccessApproximating Full Conformal Prediction at Scale via Influence Functions
Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP guarantees that the error rate is at most $\varepsilon$, irrespective of whether the underlying model is misspecified. However, the prohibitive computational costs of "full" CP led researchers to design scalable alternatives, which alas do not attain the same guarantees or statistical power of full CP. In this paper, we use influence functions to efficiently approximate full CP. We prove that our method is a consistent approximation of full CP, and empirically show that the approximation error becomes smaller as the training set increases; e.g., for $10^{3}$ training points the two methods output p-values that are $<10^{-3}$ apart: a negligible error for any practical application. Our methods enable scaling full CP to large real-world datasets. We compare our full CP approximation (ACP) to mainstream CP alternatives, and observe that our method is computationally competitive whilst enjoying the statistical predictive power of full CP. - Open Access
- 31 August 2018
- Published by Springer Nature in Machine Learning
- Vol. 108 (3) , 475-488
Majority vote ensembles of conformal predictors
- 31 August 2018
- Published by Springer Nature in Machine Learning
- Vol. 108 (3) , 475-488
Open AccessMajority vote ensembles of conformal predictors
- Open Access
- 1 October 2017
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2017 (4) , 215-231
Bayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Website Fingerprinting (WF) attacks raise major concerns about users’ privacy. They employ Machine Learning (ML) techniques to allow a local passive adversary to uncover the Web browsing behavior of a user, even if she browses through an encrypted tunnel (e.g. Tor, VPN). Numerous defenses have been proposed in the past; however, it is typically difficult to have formal guarantees on their security, which is most often evaluated empirically against state-of-the-art attacks. In this paper, we present a practical method to derive security bounds for any WF defense, where the bounds depend on a chosen feature set. This result derives from reducing WF attacks to an ML classification task, where we can determine the smallest achievable error (the Bayes error). Such error can be estimated in practice, and is a lower bound for a WF adversary, for any classification algorithm he may use. Our work has two main consequences: i) it allows determining the security of WF defenses, in a black-box manner, with respect to the state-of-the-art feature set and ii) it favors shifting the focus of future WF research to identifying optimal feature sets. The generality of this approach further suggests that the method could be used to define security bounds for other ML-based attacks.
- 1 October 2017
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2017 (4) , 215-231
Open AccessBayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Website Fingerprinting (WF) attacks raise major concerns about users’ privacy. They employ Machine Learning (ML) techniques to allow a local passive adversary to uncover the Web browsing behavior of a user, even if she browses through an encrypted tunnel (e.g. Tor, VPN). Numerous defenses have been proposed in the past; however, it is typically difficult to have formal guarantees on their security, which is most often evaluated empirically against state-of-the-art attacks. In this paper, we present a practical method to derive security bounds for any WF defense, where the bounds depend on a chosen feature set. This result derives from reducing WF attacks to an ML classification task, where we can determine the smallest achievable error (the Bayes error). Such error can be estimated in practice, and is a lower bound for a WF adversary, for any classification algorithm he may use. Our work has two main consequences: i) it allows determining the security of WF defenses, in a black-box manner, with respect to the state-of-the-art feature set and ii) it favors shifting the focus of future WF research to identifying optimal feature sets. The generality of this approach further suggests that the method could be used to define security bounds for other ML-based attacks.
- Open Access
Bayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Website Fingerprinting (WF) attacks raise major concerns about users' privacy. They employ Machine Learning (ML) to allow a local passive adversary to uncover the Web browsing behavior of a user, even if she browses through an encrypted tunnel (e.g. Tor, VPN). Numerous defenses have been proposed in the past; however, it is typically difficult to have formal guarantees on their security, which is most often evaluated empirically against state-of-the-art attacks. In this paper, we present a practical method to derive security bounds for any WF defense, which depend on a chosen feature set. This result derives from reducing WF attacks to an ML classification task, where we can determine the smallest achievable error (the Bayes error); such error can be estimated in practice, and is a lower bound for a WF adversary, for any classification algorithm he may use. Our work has two main consequences: i) it allows determining the security of WF defenses, in a black-box manner, with respect to the state-of-the-art feature set and ii) it favors shifting the focus of future WF research to the identification of optimal feature sets. The generality of the approach further suggests that the method could be used to define security bounds for other ML-based attacks.
Open AccessBayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Website Fingerprinting (WF) attacks raise major concerns about users' privacy. They employ Machine Learning (ML) to allow a local passive adversary to uncover the Web browsing behavior of a user, even if she browses through an encrypted tunnel (e.g. Tor, VPN). Numerous defenses have been proposed in the past; however, it is typically difficult to have formal guarantees on their security, which is most often evaluated empirically against state-of-the-art attacks. In this paper, we present a practical method to derive security bounds for any WF defense, which depend on a chosen feature set. This result derives from reducing WF attacks to an ML classification task, where we can determine the smallest achievable error (the Bayes error); such error can be estimated in practice, and is a lower bound for a WF adversary, for any classification algorithm he may use. Our work has two main consequences: i) it allows determining the security of WF defenses, in a black-box manner, with respect to the state-of-the-art feature set and ii) it favors shifting the focus of future WF research to the identification of optimal feature sets. The generality of the approach further suggests that the method could be used to define security bounds for other ML-based attacks.
- Open Access
- 1 April 2017
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2017 (2) , 186-203
Website Fingerprinting Defenses at the Application Layer
Website Fingerprinting (WF) allows a passive network adversary to learn the websites that a client visits by analyzing traffic patterns that are unique to each website. It has been recently shown that these attacks are particularly effective against .onion sites, anonymous web servers hosted within the Tor network. Given the sensitive nature of the content of these services, the implications of WF on the Tor network are alarming. Prior work has only considered defenses at the client-side arguing that web servers lack of incentives to adopt countermeasures. Furthermore, most of these defenses have been designed to operate on the stream of network packets, making practical deployment difficult. In this paper, we propose two application-level defenses including the first server-side defense against WF, as .onion services have incentives to support it. The other defense is a lightweight client-side defense implemented as a browser add-on, improving ease of deployment over previous approaches. In our evaluations, the server-side defense is able to reduce WF accuracy on Tor .onion sites from 69.6% to 10% and the client-side defense reduces accuracy from 64% to 31.5%.
- 1 April 2017
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2017 (2) , 186-203
Open AccessWebsite Fingerprinting Defenses at the Application Layer
Website Fingerprinting (WF) allows a passive network adversary to learn the websites that a client visits by analyzing traffic patterns that are unique to each website. It has been recently shown that these attacks are particularly effective against .onion sites, anonymous web servers hosted within the Tor network. Given the sensitive nature of the content of these services, the implications of WF on the Tor network are alarming. Prior work has only considered defenses at the client-side arguing that web servers lack of incentives to adopt countermeasures. Furthermore, most of these defenses have been designed to operate on the stream of network packets, making practical deployment difficult. In this paper, we propose two application-level defenses including the first server-side defense against WF, as .onion services have incentives to support it. The other defense is a lightweight client-side defense implemented as a browser add-on, improving ease of deployment over previous approaches. In our evaluations, the server-side defense is able to reduce WF accuracy on Tor .onion sites from 69.6% to 10% and the client-side defense reduces accuracy from 64% to 31.5%.
- 3 April 2015
- Published by Springer Nature
- p. 313-322
Conformal Clustering and Its Application to Botnet Traffic
- 3 April 2015
- Published by Springer Nature
- p. 313-322
Conformal Clustering and Its Application to Botnet Traffic