108 citations · 191 across the 8 of their papers we have counts for
9 papers
SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
Ahmed Salem, Giovanni Cherubin, David Evans +5
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of in…
Synthetic Data -- what, why and how?
James Jordon, Lukasz Szpruch, Florimond Houssiau +5
This explainer document aims to provide an overview of the current state of the rapidly expanding work on synthetic data technologies, with a particular focus on privacy. The artic…
Approximating Full Conformal Prediction at Scale via Influence Functions
Javier Abad, Umang Bhatt, Adrian Weller +1
Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification proble…
Reconstructing Training Data with Informed Adversaries
Borja Balle, Giovanni Cherubin, Jamie Hayes
Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who…
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi
Conformal Predictors (CP) are wrappers around ML models, providing error guarantees under weak assumptions on the data distribution. They are suitable for a wide range of problems,…
Bayes Security: A Not So Average Metric
Konstantinos Chatzikokolakis, Giovanni Cherubin, Catuscia Palamidessi +1
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…
Disparate Vulnerability to Membership Inference Attacks
Bogdan Kulynych, Mohammad Yaghini, Giovanni Cherubin +2
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In t…
F-BLEAU: Fast Black-box Leakage Estimation
Giovanni Cherubin, Konstantinos Chatzikokolakis, Catuscia Palamidessi
We consider the problem of measuring how much a system reveals about its secret inputs. We work under the black-box setting: we assume no prior knowledge of the system's internals,…
Bayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Giovanni Cherubin
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 beha…