Search Results for author: Georg Pichler

Found 11 papers, 6 papers with code

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

1 code implementation26 Feb 2024 Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition.

Automated Theorem Proving Out-of-Distribution Detection

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

1 code implementation2 Jun 2023 Eduardo Dadalto, Marco Romanelli, Georg Pichler, Pablo Piantanida

Misclassification detection is an important problem in machine learning, as it allows for the identification of instances where the model's predictions are unreliable.

Image Classification

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning

1 code implementation30 Mar 2022 Georg Pichler, Marco Romanelli, Leonardo Rey Vega, Pablo Piantanida

Federated Learning is expected to provide strong privacy guarantees, as only gradients or model parameters but no plain text training data is ever exchanged either between the clients or between the clients and the central server.

Federated Learning Inference Attack +1

Leveraging Adversarial Examples to Quantify Membership Information Leakage

1 code implementation CVPR 2022 Ganesh Del Grosso, Hamid Jalalzai, Georg Pichler, Catuscia Palamidessi, Pablo Piantanida

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today.

BIG-bench Machine Learning

A Differential Entropy Estimator for Training Neural Networks

1 code implementation14 Feb 2022 Georg Pichler, Pierre Colombo, Malik Boudiaf, Günther Koliander, Pablo Piantanida

Mutual Information (MI) has been widely used as a loss regularizer for training neural networks.

Domain Adaptation

Modelling the Utility of Group Testing for Public Health Surveillance

1 code implementation11 Sep 2021 Günther Koliander, Georg Pichler

Although group testing can help to significantly increase testing capabilities, the (repeated) testing of entire populations can exceed the resources of any country.

Bounding Information Leakage in Machine Learning

no code implementations9 May 2021 Ganesh Del Grosso, Georg Pichler, Catuscia Palamidessi, Pablo Piantanida

We present a novel formalism, generalizing membership and attribute inference attack setups previously studied in the literature and connecting them to memorization and generalization.

Attribute BIG-bench Machine Learning +3

Privacy-Preserving Synthetic Smart Meters Data

no code implementations6 Dec 2020 Ganesh Del Grosso, Georg Pichler, Pablo Piantanida

However, the use of power consumption data raises significant privacy concerns, as this data usually belongs to clients of a power company.

Privacy Preserving

On the Estimation of Information Measures of Continuous Distributions

no code implementations7 Feb 2020 Georg Pichler, Pablo Piantanida, Günther Koliander

In particular, we provide confidence bounds for simple histogram based estimation of differential entropy from a fixed number of samples, assuming that the probability density function is Lipschitz continuous with known Lipschitz constant and known, bounded support.

Distributed Information-Theoretic Clustering

no code implementations15 Feb 2016 Georg Pichler, Pablo Piantanida, Gerald Matz

We study a novel multi-terminal source coding setup motivated by the biclustering problem.

Clustering Two-sample testing

Cannot find the paper you are looking for? You can Submit a new open access paper.