3.1.1 Three way optimization between privacy and utility

One of the main problems in the design of privacy mechanisms is the preservation of the utility. In the case of local privacy, namely when the data are sanitized by the user before they are collected, the notion of utility is twofold:

• Utility as quality of service (QoS):
  The user usually gives his data in exchange of some service, and in general the quality of the service depends on the precision of such data. For instance, consider a scenario in which Alice wants to use a LBS (Location-Based Service) to find some restaurant near her location $x$. The LBS needs of course to know Alice's location, at least approximately, in order to provide the service. If Alice is worried about her privacy, she may send to the LBS an approximate location $x^{\text{'}}$ instead of $x$. Clearly, the LBS will send a list of restaurants near $x$, so if $x^{\text{'}}$ is too far from $x$ the service will degrade, while if it is too close Alice's privacy would be at stake.
• Utility as statistical quality of the data (Stat):
  Bob, the service provider, is motivated to offer his service because in this way he can collect Alice's data, and quality data are very valuable for the big-data industry. We will consider in particular the use of the data collections for statistical purposes, namely for extracting general information about the population (and not about Alice as an individual). Of course, the more Alice's data are obfuscated, the less statistical value they have.

We intend to consider both kinds of utility, and study the “three way” optimization problem in the context of $d$-privacy, our approach to local differential privacy  34. Namely, we want to develop methods for producing mechanisms that offer the best trade-off between $d$-privacy, QoS and Stat, at the same time. In order to achieve this goal, we will need to investigate various issues. In particular:

• how to best estimate the original distribution from a collection of noisy data, in order to perform the intended statistical analysis,
• what metrics to use for assessing the statistical value of a distributions (for a given application), in order to reason about Stat, and
• how to compute in an efficient way the best noise from the point of view of the trade-off between $d$-privacy, QoS and Stat.

Estimation of the original distribution

The only methods for the estimation of the original distribution from perturbed data that have been proposed so far in the literature are the iterative Bayesian update (IBU) and the matrix inversion (INV). The IBU is more general and based on solid statistical principles, but it is not ye well known in the in the privacy community, and it has not been studied much in this context. We are motivated to investigate this method because from preliminary experiments it seems more efficient on date obfuscated by geo-indistinguishability mechanisms (cfr. next section). Furthermore, we believe that the IBU is compositional, namely it can deal naturally and efficiently with the combination of data generated by different noisy functions, which is important since in the local model of privacy every user can, in principle, use a different mechanisms or a different level of noise. We intend to establish the foundations of the IBU in the context of privacy, and study its properties like the compositionality mentioned above, and investigate its performance in the state-of-the-art locally differentially private mechanisms.

Hybrid model

An interesting line of research will be to consider an intermediate model between the local and the central models of differential privacy (cfr. Figure 1). The idea is to define a privacy mechanism based on perturbing the data locally, and then collecting them into a dataset organized as an histogram. We call this model “hibrid” because the collector is trusted like in central differential privacy, but the data are sanitized according to the local model. The resulting dataset would satisfy differential privacy from the point of view of an external observer, while the statistical utility would be as high as in the local model. One further advantage is that the IBU is compositional, hence the datasets sanitized in this way could be combined without any loss of precision in the application of the IBU. In other words, the statistical utility of the union of sanitized datasets is the same as the statistical utility of the sanitized union of datasets, which is of course an improvement (for the law of large numbers) wrt each separate dataset. One important application would be the cooperative sharing of sanitized data owned by different different companies or institution, to the purpose of improving statistical utility while preserving the privacy of their respective datasets.

Geo-indistinguishability: a framework to protect the privacy of the user when dealing with location-based services (a). The framework guarrantees dd-privacy, a distance-based variant of differential privacy (b). The typical implementation uses (extended) Laplace noise (c).

3.1.2 Geo-indistinguishability

We plan to further develop our line of research on location privacy, and in particular, enhance our framework of geo-indistinguishability 4 (cfr. Figure 2) with mechanisms that allow to take into account sanitize high-dimensional traces without destroying utility (or privacy). One problem with the geo-indistinguishable mechanisms developed so far (the planar Laplace an the planar geometric) is that they add the same noise function uniformly on the map. This is sometimes undesirable: for instance, a user located in a small island in the middle of a lake should generate much more noise to conceal his location, so to report also other locations on the ground, because the adversary knows that it is unlikely that the user is in the water. Furthermore, for the same reason, it does not offer a good protection with respect to re-identification attacks: a user who lives in an isolated place, for instance, can be easily singled out because he reports locations far away from all others. Finally, and this is a common problem with all methods based on DP, the repeated use of the mechanism degrades the privacy, and even when the degradation is linear, as in the case of all DP-based methods, it becomes quickly unacceptable when dealing with highly structured data such as spatio-temporal traces.

3.1.3 Threats for privacy in machine learning

In recent years several researchers have observed that machine learning models leak information about the training data. In particular, in certain cases an attacker can infer with relatively high probability whether a certain individual participated in the dataset (membership inference attack) od the value of his data (model inversion attack). This can happen even if the attacker has nop access to the internals of the model, i.e., under the black box assumption, which is the typical scenario when machine learning is used as a service (cfr. Figure 3). We plan to develop methods to reason about the information-leakage of training data from deep learning systems, by identifying appropriate measures of leakage and their properties, and use this theoretical framework as a basis for the analysis of attacks and for the development of robust mitigation techniques. More specifically, we aim at:

• Developing compelling case studies based on state-of-the-art algorithms to perform attacks, showcasing the feasibility of uncovering specified sensitive information from a trained software (model) on real data.
• Quantifying information leakage. Based on the uncovered attacks, the amount of sensitive information present in trained software will be quantified and measured. We will study suitable notions of leakage, possibly based on information-theoretical concepts, and establish firm foundations for these.
• Mitigating information leakage. Strategies will be explored to avoid the uncovered attacks and minimize the potential information leakage of a trained model.

3.1.4 Relation between privacy and robustness in machine learning

The relation between privacy and robustness, namely resilience to adversarial attacks, is rather complicated. Indeed the literature on the topic seems contradictory: on the one hand, there are works that show that differential privacy can help to mitigate both the risk of inference attacks and of misclassification (cfr. 40). On the other hand, there are studies that show that there is a trade-off between protection from inference attacks and robustness 43. We intend to shed light on this confusing situation. We believe that the different variations of differential privacy play a role in this apparent contradiction. In particular, preprocessing the training data with $d$-privacy seems to go along with the concept of robustness, because it guarantees that small variations in the input cannot result in large variations in the output, which is exactly the principle of robustness. On the other hand, the addition of random noise on the output result (postprocessing), which is the typical method in central DP, should reduce the precision and therefore increase the possibility of misclassification. We intend to make a taxonomy of the differential privacy variants, in relation to their effect on robustness, and develop a principled approach to protect both privacy and security in an optimal way.

One promising research direction for the deployment of $d$-privacy in this context is to consider Bayesian neural networks (BNNs). These are neural networks with distributions over their weights, which can capture the uncertainty within the learning model, and which provide a natural notion of distance (between distributions) on which we can define a meaningful notion of $d$-privacy. Such neural networks allow to compute an uncertainty estimate along with the output, which is important for safety-critical applications.

3.1.5 Relation between privacy and fairness

Both fairness and privacy are multi-faces notions, assuming different meaning depending on the application domain, on the situation, and on what exactly we want to protect. Fairness, in particular, has received many different definitions, some even in contrast with each other. One of the definitions of fairness is the property that similar “similar” input data produce "similar" outputs. Such notion corresponds closely to $d$-privacy. Other notions of fairness, however, are in opposition to standard differential privacy. This is the case, notably, of Equalized Odds36 and of Equality of False Positives and Equality of False Negatives35. We intend to study a tassonomy of the relation between the main notions of fairness an the various variants of differential privacy. In particular, we intend to study the relation between the recently-introduced notions of causal fairness and causal differential privacy  44.

Another line of research related to privacy and fairness, that we intend to explore, is the design of to pre-process the training set so to obtain machine learning models that are both privacy-friendly and fair.

3.2.1 Non-0-sum games

The framework of $g$-leakage does not take into account two important factors: (a) the loss of the user, and (b) the cost of the attack for the adversary. Regarding (a), we observe that in general the goal of the adversary may not necessarily coincide with causing maximal damage to the user, i.e., there may be a mismatch between the aims of the attacker and what the user tries to protect the most. To model this more general scenario, we had started investigating the interplay between defender and attacker in a game-theoretic setting, starting with the simple case of 0-sum games which corresponds to $g$-leakage. The idea was that, once the simple 0-sum case would be well understood, we would extend the study to the non-0-sum case, that is needed to represent (a) and (b) above. However, we had first to invent and lay the foundations of a new kind of games, the information leakage games32 because the notion of leakage cannot be expressed in terms of payoff in standard game theory. Now that the theory of these new games is well established, we intend to go ahead with our plan, namely study costs and damages of attacks in terms of non-0-sum information leakage games.

3.2.2 Black-box estimation of leakage via machine learning

Most of the works in QIF rely on the so-called white-box assumption, namely, they assume that it is possible to compute exactly the (probabilistic) input-output relation of the system, seen as an information-theoretic channel. This is necessary in order to apply the formula that expresses the leakage. In practical situations, however, it may not be possible to compute the input-output relation, either because the system is too complicated, or simply because it is not accessible. Such scenario is called black-box. The only assumption we make is that the adversary can interact with the system, by feeding to it inputs of his choice and observing the corresponding outputs.

Given the practical interest of the black-box model, we intend to study methods to estimate its leakage. Clearly the standard QIF methods are not applicable. We plan to use, instead, a machine learning approach, continuing the work we started in 42. In particular, we plan to investigate whether we can improve the efficiency of the method proposed by leveraging on the experience that we have acquired with the GANs 41. The idea is to construct a training set and a testing set from the input-output samples collected by interacting with the system, and then build a classifier that learns from the training set to classify the input from the output so to maximize its gain. The measure of its performance on the testing set should then give an estimation of the posterior $g$-vulnerability.

3.3.1 Privacy protection

In 38 we have investigated potential leakage in social networks, namely, the unintended propagation and collection of confidential information. We intend to enrich this model with epistemic aspects, in order to take into account the belief of the users and how it influences the behavior of agents with respect the transmission of information.

Furthermore, we plan to investigate attack models used to reveal a user’s private information, and explore the framework of $g$-leakage to formalize the privacy threats. This will provide the basis to study suitable protection mechanisms.

3.3.2 Polarization and Belief in influence graphs

In social scenarios, a group may shape their beliefs by attributing more value to the opinions of influential figures. This cognitive bias is known as authority bias. Furthermore, in a group with uniform views, users may become extreme by reinforcing one another’s opinions, giving more value to opinions that confirm their own beliefs; another common cognitive bias known as confirmation bias. As a result, social networks can cause their users to become radical and isolated in their own ideological circle causing dangerous splits in society (polarization). We intend to study these dynamics in a model called influence graph, which is a weighted directed graph describing connectivity and influence of each agent over the others. We will consider two kinds of belief updates: the authority belief update, which gives more value to the opinion of agents with higher influence, and the confirmation bias update, which gives more value to the opinion of agents with similar views.

We plan to study the evolution of polarization in these graphs. In particular, we aim at defining a suitable measure of polarization, characterizing graph structures and conditions under which polarization eventually converges to 0 (vanishes), and methods to compute the change in the polarization value over time.

Another purpose of this line of research is how the bias of the agents whose data are being collected impacts the fairness of learning algorithms based on these data.

3.3.3 Concurrency models for the propagation of information

Due to their popularity and computational nature, social networks have exacerbated group polarization. Existing models of group polarization from economics and social psychology state its basic principles and measures 37. Nevertheless, unlike our computational ccp models, they are not suitable for describing the dynamics of agents in distributed systems. Our challenge is to coherently combine our ccp models for epistemic behavior with principles and techniques from economics and social psychology for GP. We plan to develop a ccp-based process calculus which incorporates structures from social networks, such as communication, influence, individual opinions and beliefs, and privacy policies. The expected outcome is a computational model that will allow us to specify the interaction of groups of agents exchanging epistemic information among them and to predict and measure the leakage of private information, as well as the degree of polarization that such group may reach.

7.1.1 Location Guard

• Keywords:
  Privacy, Geolocation, Browser Extensions
• Scientific Description:
  The purpose of Location Guard is to implement obfuscation techniques for achieving location privacy, in a an easy and intuitive way that makes them available to the general public. Various modern applications, running either on smartphones or on the web, allow third parties to obtain the user's location. A smartphone application can obtain this information from the operating system using a system call, while web application obtain it from the browser using a JavaScript call.
• Functional Description:

  Websites can ask the browser for your location (via JavaScript). When they do so, the browser first asks for your permission, and if you accept, it detects your location (typically by transmitting a list of available wifi access points to a geolocation provider such as Google Location Services, or via GPS if available) and gives it to the website.

  Location Guard is a browser extension that intercepts this procedure. The permission dialog appears as usual, and you can still choose to deny it. If you give permission, then Location Guard obtains your location and adds "random noise" to it, creating a fake location. Only the fake location is then given to the website.

  Location Guard is by now a stable tool with a large user base. No new features were added in 2020, however, the tool is still actively maintained.

• URL:
  https://­github.­com/­chatziko/­location-guard
• Contact:
  Konstantinos Chatzikokolakis
• Participants:
  Catuscia Palamidessi, Konstantinos Chatzikokolakis, Marco Stronati, Miguel Andrés, Nicolas Bordenabe

7.1.2 IBU: A java library for estimating distributions

• Keywords:
  Privacy, Statistic analysis, Bayesian estimation
• Functional Description:

  The main objective of this library is to provide an experimental framework for evaluating statistical properties on data that have been sanitized by obfuscation mechanisms, and for measuring the quality of the estimation. More precisely, it allows modeling the sensitive data, obfuscating these data using a variety of privacy mechanisms, estimating the probability distribution on the original data using different estimation methods, and measuring the statistical distance and the Kantorovich distance between the original and estimated distributions. This is one of the main software projects of Palamidessi's ERC Project HYPATIA.

  We intend to extend the software with functionalities that will allow estimating statistical properties of multi-dimensional (locally sanitized) data and using collections of data locally sanitized with different mechanisms.

• URL:
  https://­gitlab.­com/­locpriv/­ibu
• Contact:
  Ehab ElSalamouny

7.1.3 libqif - A Quantitative Information Flow C++ Toolkit Library

• Keywords:
  Information leakage, Privacy, C++, Linear optimization
• Functional Description:

  The goal of libqif is to provide an efficient C++ toolkit implementing a variety of techniques and algorithms from the area of quantitative information flow and differential privacy. We plan to implement all techniques produced by Com$\setminus$`ete in recent years, as well as several ones produced outside the group, giving the ability to privacy researchers to reproduce our results and compare different techniques in a uniform and efficient framework.

  Some of these techniques were previously implemented in an ad-hoc fashion, in small, incompatible with each-other, non-maintained and usually inefficient tools, used only for the purposes of a single paper and then abandoned. We aim at reimplementing those – as well as adding several new ones not previously implemented – in a structured, efficient and maintainable manner, providing a tool of great value for future research. Of particular interest is the ability to easily re-run evaluations, experiments, and case-studies from QIF papers, which will be of great value for comparing new research results in the future.

  The library's development continued in 2020 with several new added features. 68 new commits were pushed to the project's git repository during this year. The new functionality was directly applied to the experimental results of several publications of COMETE.

• URL:
  https://­github.­com/­chatziko/­libqif
• Contact:
  Konstantinos Chatzikokolakis

7.1.4 Multi-Freq-LDPy

• Name:
  Multiple Frequency Estimation Under Local Differential Privacy in Python
• Keywords:
  Privacy, Python, Benchmarking
• Scientific Description:
  The purpose of Multi-Freq-LDPy is to allow the scientific community to benchmark and experiment with Locally Differentially Private (LDP) frequency (or histogram) estimation mechanisms. Indeed, estimating histograms is a fundamental task in data analysis and data mining that requires collecting and processing data in a continuous manner. In addition to the standard single frequency estimation task, Multi-Freq-LDPy features separate and combined multidimensional and longitudinal data collections, i.e., the frequency estimation of multiple attributes, of a single attribute throughout time, and of multiple attributes throughout time.
• Functional Description:

  Local Differential Privacy (LDP) is a gold standard for achieving local privacy with several real-world implementations by big tech companies such as Google, Apple, and Microsoft. The primary application of LDP is frequency (or histogram) estimation, in which the aggregator estimates the number of times each value has been reported.

  Multi-Freq-LDPy provides an easy-to-use and fast implementation of state-of-the-art LDP mechanisms for frequency estimation of: single attribute (i.e., the building blocks), multiple attributes (i.e., multidimensional data), multiple collections (i.e., longitudinal data), and both multiple attributes/collections.

  Multi-Freq-LDPy is now a stable package, which is built on the well-established Numpy package - a de facto standard for scientific computing in Python - and the Numba package for fast execution.

• URL:
  https://­github.­com/­hharcolezi/­multi-freq-ldpy
• Publication:
  hal-03816212
• Contact:
  Heber Hwang Arcolezi
• Participants:
  Heber Hwang Arcolezi, Jean-François Couchot, Sébastien Gambs, Catuscia Palamidessi, Majid Zolfaghari

9.1.1 Inria associate team not involved in an IIL or an international program

9.1.2 Participation in other International Programs

9.2.1 Visits of international scientists

9.2.2 Visits to international teams

9.3.1 Horizon Europe

9.3.2 H2020 projects

9.3.3 Other european programs/initiatives

iPOP

Participants: Catuscia Palamidessi, Sami Zhioua, Héber Arcolezi, Sayan Biswas, Ruta Binkyte-Sadauskiene, Karima Makhlouf.

• Web Page:
  Link
• Title:
  Interdisciplinary Project on Privacy
• Program:
  PEPR Cybersecurity
• Duration:
  1 October 2022 - 30 September 2028
• Coordinators:
  Antoine Boutet (Insa-Lyon) - Vincent Roca (Inria)
• Partners:
  • Inria
  • CNRS
  • CNIL
  • INSA-Centre Val de Loire (CVL)
  • INSA-Lyon
  • Université Grenoble Alpes
  • Université de Lille
  • Université Rennes 1
  • Université de Versailles Saint-Quentin-en-Yvelines
• Inria COMETE contact:
  Catuscia Palamidessi
• Description:
  Digital technologies provide services that can greatly increase quality of life (e.g. connected e-health devices, location based services or personal assistants). However, these services can also raise major privacy risks, as they involve personal data, or even sensitive data. Indeed, this notion of personal data is the cornerstone of French and European regulations, since processing such data triggers a series of obligations that the data controller must abide by. This raises many multidisciplinary issues, as the challenges are not only technological, but also societal, judiciary, economic, political and ethical. The objectives of this project are thus to study the threats on privacy that have been introduced by these new services, and to conceive theoretical and technical privacy-preserving solutions that are compatible with French and European regulations, that preserve the quality of experience of the users. These solutions will be deployed and assessed, both on the technological and legal sides, and on their societal acceptability. In order to achieve these objectives, we adopt an interdisciplinary approach, bringing together many diverse fields: computer science, technology, engineering, social sciences, economy and law.

FedMalin

Participants: Catuscia Palamidessi, Sami Zhioua, Héber Arcolezi, Sayan Biswas, Ruta Binkyte-Sadauskiene, Karima Makhlouf.

• Web Page:
  Link
• Title:
  Federated MAchine Learning over the INternet
• Program:
  Inria Challenge
• Duration:
  1 October 2022 - 30 September 2026
• Coordinators:
  Aurélien Bellet and Giovanni Neglia
• Partners:
  • ARGO (Inria Paris)
  • COATI (Inria Sophia)
  • COMETE (Inria Saclay)
  • EPIONE (Inria Sophia)
  • MAGNET (Inria Lille)
  • MARACAS (Inria Lyon)
  • NEO (Inria Sophia)
  • SPIRALS (Inria Lille)
  • TRIBE (Inria Saclay)
  • WIDE (Inria Rennes)
• Inria COMETE contact:
  Catuscia Palamidessi
• Description:
  In many use-cases of Machine Learning (ML), data is naturally decentralized: medical data is collected and stored by different hospitals, crowdsensed data is generated by personal devices, etc. Federated Learning (FL) has recently emerged as a novel paradigm where a set of entities with local datasets collaboratively train ML models while keeping their data decentralized. FedMalin aims to push FL research and concrete use-cases through a multidisciplinary consortium involving expertise in ML, distributed systems, privacy and security, networks, and medicine. We propose to address a number of challenges that arise when FL is deployed over the Internet, including privacy and fairness, energy consumption, personalization, and location/time dependencies. FedMalin will also contribute to the development of open-source tools for FL experimentation and real-world deployments, and use them for concrete applications in medicine and crowdsensing.

LOST2DNN

Participants: Catuscia Palamidessi, Ganesh Del Grosso, Federica Granese, Pablo Piantanida.

• Web Page:
  Link
• Title:
  Leakage of Sensitive Training Data from Deep Neural Networks
• Program:
  DATAIA Call for Research Projects
• Duration:
  October 1, 2019 - September 30, 2022
• Coordinators:
  Catuscia Palamidessi and Pablo Piantanida
• Partners:
  • Inria, Catuscia Palamidessi
  • Centrale Supélec, Pablo Piantanida
  • TU Wien, Austria (Associate). Georg Pichler
• Inria contact:
  Catuscia Palamidessi
• Description:
  The overall project goal is to develop a fundamental understanding with experimental validation of the information-leakage of training data from deep learning systems. We plan to establish the foundations for a suitable measure of leakage which will serve as a basis for the analysis of attacks and for the development of robust mitigation techniques.

10.1.1 Scientific events: organisation

The team Comete has organized a workshop on ethical AI. Campus de l'Ecole Polytechnique, Palaiseau, 30 September 2022

10.1.2 Scientific events: selection

Catuscia Palamidessi has been member of the selection committee of the following conferences and workshops:

• FOSSACS 2024. The 27th International Conference on Foundations of Software Science and Computation Structures. (Part of ETAPS 2024.) Luxembourg, 2024.
• CSF 2023. The 36th IEEE Computer Security Foundations Symposium. Dubrovnik, Croatia, July 10 - 14, 2023.
• LICS 2023. The Thirty-Eighth Annual ACM/IEEE Symposium on Logic in Computer Science. Boston, USA, 26–29 June 2023.
• FACS 2022. The 18th International Conference on Formal Aspects of Component Software. Oslo, Norway, 10-11 November 2022.
• Senior PC member of PETS 2022. The 22nd Privacy Enhancing Technologies Symposium. Sydney, Australia. July 11–15, 2022.
• FORTE 2022. The 42nd International Conference on Formal Techniques for Distributed Objects, Components, and Systems. Lucca, Italy, June 13-17, 2022
• EuroS&P 2022. The 7th IEEE European Symposium on Security and Privacy. Genoa, Italy. June 6-10, 2022.
• CSF 2022. The 35th IEEE Computer Security Foundations Symposium. Co-located with FLoC 2022. Haifa, Israel, August 2022.
• SDS 2023. The 10th IEEE Swiss Conference on Data Science. Zurich, Switzelrland, June 22 – 23, 2023.
• WIL 2023. The 7th Women in Logic Workshop. Rome, Italy, June 1st , 2023.
• FTSCS 2022. The 8th International Workshop on Formal Techniques for Safety-Critical Systems. Auckland, New Zealand, December 7, 2022.
• PPAI 2022. The 3rd AAAI Workshop on Privacy-Preserving Artificial Intelligence. Online. February 28, 2022.
• CIRM Logic and Interaction thematic month: Logical Foundations of Probabilistic Programming. Lineal Logic International Research Network. Luminy, France. Spring 2022.

Frank Valencia has been member of the selection committee of the following conferences and workshops:

• FOSSACS 2023. The 26th International Conference on Foundations of Software Science and Computation Structures. (Part of ETAPS 2023.) Paris, 22-27 April 2023.
• ICLP 2023. 39th International Conference on Logic Programming. London, July 9 - 15, 2023
• CLEI 2022. The 48th International Latin American Conference on Informatics. Armenia, Colombia, 17-21 October 2022.
• ICLP-DC 2022 The 38th International Conference on Logic Programming (ICLP) - DC. Haifa, Israel, July 31-August 8, 2022.

10.1.3 Journals

Catuscia Palamidessi is member of the editorial board of the following journals:

• (2022-) Member of the Editorial Board of the ACM Transactions on Privacy and Security (TOPS), ACM.
• (2021-22) Member of the Editorial Board of Proceedings on Privacy Enhancing Technologies (PoPETs), De Gruyter.
• (2021-) Member of the Editorial Board of TheoretiCS, a diamond Open Access journal published by Episciences .
• (2020-) Member of the Editorial Board of the IEEE Transactions on Dependable and Secure Computing. IEEE Computer Society.
• (2020-) Member of the Editorial Board of the Journal of Logical and Algebraic Methods in Programming, Elsevier.
• (2019-) Member of the Editorial Board of the Journal of Computer Security. IOS Press.
• (2015-) Member of the Editorial Board of Acta Informatica, Springer.
• (2006-) Member of the Editorial Board of Mathematical Structures in Computer Science, Cambridge University Press.

10.1.4 Invited talks

Catuscia Palamidessi has given the following invited talks:

• FLOC 2022. Keynote speaker at the Federated Logic Conference. Haifa, Israel, July-August 2022.
• AFCP 2022. The NeurIPS workshop on Algorithmic Fairness through the Lens of Causality and Privacy. New Orleans, USA, December 3, 2022.
• Talk on Differential Privacy at the Collège de France. 24 March 2022.

Frank Valencia has given the following invited talk:

• IEEE ComSoc SIoA SIG Invited Speaker at the IEEE Social Networks Technical Committee SIG Seminar on Modelling Bias and Polarization in Social Networks. 28 October 20222.

10.1.5 Leadership within the scientific community

Since July 2002 Catuscia palamidessi is Chair of SIGLOG, the ACM Special Interest Group on Logic and Computation.

10.1.6 Scientific expertise

Catuscia Palamidessi is/has been:

• (2021-) Member of the Board of Trustees of the IMDEA Software Institute.
• (2019-22) Member of the Scientific Advisory Board of ANSSI, the French National Cybersecurity Agency.
• (2019-) Member of the Scientific Advisory Board of CISPA, the Helmholtz Center for Information Security.
• (2016-) Member of the Steering Committee of CONCUR, the International Conference in Concurrency Theory.
• (2015-) Member of the Steering Committee of EACSL, the European Association for Computer Science Logics.
• (2023) Member of the committee for a faculty position at the ETH Zurich, Switzerland.
• (2023) Member of the committee for a professor position at the INSA Lyon, France.
• (2022-23) Member of the committee for the UK-US Prize Challenge on Advancing Privacy-Preserving Federated Learning. Sponsored by NIST and NSF.
• (2022) Member of the review panel for the Italian Ministry of Universities and Research research grants.
• (2022) Member of the review panel for the Swiss National Science Foundation advanced grants.
• (2022) Member of the review panel for the Estonian Research Council grants.
• (2022) Member of the review panel for the Swedish Research Council consolidator grants.
• (2022) Member of the committee for the CCS Test-of-Time Award.
• (2022) Member of the committee for a professor position at the Université Sorbonne Paris Nord, France.

10.2.1 Teaching

Frank Valencia has been teaching a Discrete Math course and Computability course at la Pontificia Universidad Javeriana. Each course consists 42 hours of lectures.

Catuscia Palamidessi has given the following courses:

• Course on Privacy at the ELSA Summer school on Trustworthy AI. Saarbrücken, Germany. September 2022.
• Course on Privacy and Fairness at the IDESSAI, the second Inria-DFKI European Summer School on AI. Saarbrücken, Germany. August-September 2022.

10.2.2 Supervision

In COMETE we are supervising the following PhD students:

• (2023-) Ramon Gonze. IPP and Federal University of Minas Gerais. Co-supervised by Catuscia Palamidessi and by Mario Alvim. Thesis subject: Bayesian guarrantees of differential privacy.
• (2022-) Andreas Athanasiou. IPP and University of Athens. Co-supervised by Catuscia Palamidessi and by Kostantinos Chatzikokolakis. Thesis subject: The shuffle model for d-privacy.
• (2021-) Karima Makhlouf. IPP. Thesis subject: Relation between privacy and fairness in machine learning. Co-supervised by Catuscia Palamidessi and by Héber Arcolezi.
• (2020-) Ruta Binkite-Saudaskiene. IPP. Co-supervised by Catuscia Palamidessi and by Sami Zhioua. Thesis subject: Fairness and Privacy in machine learning: interdisciplinary approach.
• (2020-) Sayan Biswas. IPP. Supervised by Catuscia Palamidessi. Thesis subject: On the tradeoff between Local Differential Privacy and Statistical Utility.
• (2020-) Carlos Pinzon. IPP.
• (2020-) Sayan Biswas. IPP. Co-supervised by Catuscia Palamidessi, Pablo Piantanida and Frank Valencia. Thesis subject: On the tradeoff between Privacy and Fairness in Machine Learning.
• (2019-) Federica Granese. IPP and Università di Roma "La Sapienza". Co-supervised by Catuscia Palamidessi, Daniele Gorla and Pablo Piantanida. Thesis subject: Security in Machine Learning.
• (2019-) Ganesh Del Grosso Guzman. IPP. Co-supervised by Catuscia Palamidessi and by Pablo Piantanida. Thesis subject: Privacy in Machine Learning.

In 2022, in COMETE we have supervised the following master students and interns:

• Simon Sebastian. Bacelor student, IPP, France. Co-supervised by Carlos Pinzon and Catuscia Palamidessi. From May 2022 until August 2022.
• Cesara Petrui. Bacelor student, IPP, France. Co-supervised by Carlos Pinzon and Catuscia Palamidessi. From May 2022 until August 2022.
• Filippo Galli. Visiting PhD student, ENS Pisa, Italy. Supervised by Catuscia Palamidessi. From Sept 2021 until March 2022.

10.2.3 Other advisory activity

Catuscia Palamidessi is member of the advisory boards for PhD programs and thesis:

• (2022-24) Member of the advising committee for Martina Cinquini, PhD student supervised by Salvatore Ruggieri, University of Pisa, Italy.
• (2012-) External member of the scientific council for the PhD in Computer Science at the University of Pisa, Italy.
• (2020-22) Member of the advising committee of Abhishek Sharma, PhD student supervised by Maks Ovsjanikov, IPP, France.

10.2.4 Juries

Catuscia Palamidessi has been member of the jury in the following PhD defenses:

• Guilherme Alves (LORIA, France). Member of the committee board at the PhD defense. Title of the thesis: Hybrid Approaches for Algorithmic Fairness. Advised by Miguel Couceiro and Amedeo Napoli. Defended in December 2022.
• Elli Anastasiadi (Reykjavik University, Island). Member of the committee board at the PhD defense. Title of the thesis: Runtime and Equational Verification of Concurent Systems. Advised by Luca Aceto and Anna Ingólfsdóttir. Defended in October 2022.
• Arthur Américo (Queen Mary University of London, UK). PhD thesis reviewer and member of the committee at the PhD defense. Title of the thesis: From Quantitative Information Flow to Information Theory and Quantum Leakage. Advised by Pasquale Malacaria. Defended in September 2022.
• Vincent Grari (University of Sorbonne, France). Member of the committee at the PhD defense. Title of the thesis: Adversarial mitigation to reduce unwanted biases in machine learning. Advised by Marcin Detyniecki and Sylvain Lamprier. Defended in June 2022.

10.3.1 Articles and contents

Frank Valencia has interviewed for the following media:

• Chut! Interview Les réseaux sociaux fournissent le milieu idéal pour la prolifération des biais cognitifs. Jan 12, 2023.
• Inria Website Interview on Social networks: Can mathematical modeling help reduce polarization of opinions? May 11, 2022.
• ToT Curses Article on Un modéle mathématique pour réduire la polarisation des opinions. May 18, 2022.
• Cali24horas Radio Interview on Polarization on Social Media. March 17, 2022.

10.3.2 Interventions

Catuscia Palamidessi is invited speaker at EMW 2023, the ETAPS Mentoring Workshop. This workshop aims at encouraging graduate students and senior undergraduate students to pursue careers in programming language research, and at educating them on the research career. 23 April 2023

International journals

• 11 articleM. S.Mário S. Alvim, B.Bernardo Amorim, S.Sophia Knight, S.Santiago Quintero and F.Frank Valencia. A Formal Model for Polarization under Confirmation Bias in Social Networks.Logical Methods in Computer ScienceDecember 2022
  HALback to textback to textback to text
• 12 articleM. S.Mário S. Alvim, K.Konstantinos Chatzikokolakis, Y.Yusuke Kawamoto and C.Catuscia Palamidessi. Information Leakage Games: Exploring Information as a Utility Function.ACM Transactions on Privacy and Security2022
  HALDOIback to text
• 13 articleH. H.Héber Hwang Arcolezi, J.-F.Jean-François Couchot, B.Bechara Al Bouna and X.Xiaokui Xiao. Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates.Digital Communications and NetworksJuly 2022
  HALDOIback to text
• 14 articleH. H.Héber Hwang Arcolezi, J.-F.Jean-François Couchot, D.Denis Renaud, B.Bechara Al Bouna and X.Xiaokui Xiao. Differentially private multivariate time series forecasting of aggregated human mobility with deep learning: Input or gradient perturbation?Neural Computing and Applications34June 2022, 13355–13369
  HALDOIback to text

International peer-reviewed conferences

• 15 inproceedingsH. H.Héber Hwang Arcolezi, J.-F.Jean-François Couchot, S.Sébastien Gambs, C.Catuscia Palamidessi and M.Majid Zolfaghari. Multi-Freq-LDPy: Multiple Frequency Estimation Under Local Differential Privacy in Python.ESORICS 2022 - European Symposium on Research in Computer Security13556Lecture Notes in Computer ScienceCopenhague, DenmarkSpringer Nature SwitzerlandSeptember 2022, 770 - 775
  HALDOIback to text
• 16 inproceedingsR.Rūta Binkytė-Sadauskienė, K.Karima Makhlouf, C.Carlos Pinzón, S.Sami Zhioua and C.Catuscia Palamidessi. Causal Discovery for Fairness.Proceedings of the 3rd Workshop on Algorithmic Fairness through the Lens of Causality and Privacy (AFCP 2022)Algorithmic Fairness through the Lens of Causality and Privacy (AFCP) - Workshop affiliated with Neural Information Processing systems (NeurIPS )New Orleans, United StatesDecember 2022
  HALback to text
• 17 inproceedingsS.Sayan Biswas, G.Graham Cormode and C.Carsten Maple. Impact of sampling on locally differentially private data collection.Proceedings of the Eight Conference on Competitive Advantage in the Digital Economy (CADE)CADE 2022 - Competitive Advantage in the Digital EconomyVenice, ItalyInstitution of Engineering and Technology; IEEEJune 2022, 64-70
  HALDOI
• 18 inproceedingsS.Sayan Biswas, K.Kangsoo Jung and C.Catuscia Palamidessi. Tight Differential Privacy Blanket for the Shuffle Model.Proceedings of the Eight International Conference on Competitive Advantage in the Digital Economy (CADE 2022)CADE 2022 - Competitive Advantage in the Digital EconomyVenice, ItalyIET Digital Library; IEEE XploreJune 2022, 61-63
  HALDOIback to text
• 19 inproceedingsG.Ganesh Del Grosso, H.Hamid Jalalzai, G.Georg Pichler, C.Catuscia Palamidessi and P.Pablo Piantanida. Leveraging Adversarial Examples to Quantify Membership Information Leakage.Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)New Orleans, United StatesIEEEJune 2022, 10389-10399
  HALDOIback to text
• 20 inproceedingsN.Natasha Fernandes, A.Annabelle Mciver, C.Catuscia Palamidessi and M.Ming Ding. Universal Optimality and Robust Utility Bounds for Metric Differential Privacy.2022 IEEE 35th Computer Security Foundations Symposium (CSF)Haifa, IsraelIEEEAugust 2022, 348-363
  HALDOIback to text
• 21 inproceedingsF.Federica Granese, M.Marine Picot, M.Marco Romanelli, F.Francisco Messina and P.Pablo Piantanida. MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors.Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2022)European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in DatabasesGrenoble, FranceJune 2022
  HALback to text
• 22 inproceedingsC.Carlos Pinzón, C.Catuscia Palamidessi, P.Pablo Piantanida and F.Frank Valencia. On the Impossibility of non-Trivial Accuracy in Presence of Fairness Constraints.Proceedings of the AAAI 36th Conference on Artificial Intelligence36Proceedings7Vancouver / Virtual, CanadaJune 2022, 7993-8000
  HALDOIback to text

Conferences without proceedings

• 23 inproceedingsF.Filippo Galli, S.Sayan Biswas, K.Kangsoo Jung, T.Tommaso Cucinotta and C.Catuscia Palamidessi. Group privacy for personalized federated learning.International Workshop on Federated Learning: Recent Advances and New Challenges in Conjunction with NeurIPS 2022 (FL-NeurIPS'22)New Orleans, United StatesDecember 2022
  HAL

Reports & preprints

• 24 miscG.Guilherme Alves, F.Fabien Bernier, M.Miguel Couceiro, K.Karima Makhlouf, C.Catuscia Palamidessi and S.Sami Zhioua. Survey on Fairness Notions and Related Tensions.June 2022
  HAL
• 25 miscH. H.Héber Hwang Arcolezi, C.Carlos Pinzón, C.Catuscia Palamidessi and S.Sébastien Gambs. Frequency Estimation of Evolving Data Under Local Differential Privacy.December 2022
  HAL
• 26 miscS.Sayan Biswas and C.Catuscia Palamidessi. PRIVIC: A privacy-preserving method for incremental collection of location data.2022
  HAL
• 27 miscH.Hamid Jalalzai, E.Elie Kadoche, R.Rémi Leluc and V.Vincent Plassier. Membership Inference Attacks via Adversarial Examples.December 2022
  HAL
• 28 miscK.Karima Makhlouf, S.Sami Zhioua and C.Catuscia Palamidessi. Identifiability of Causal-based Fairness Notions: A State of the Art.January 2023
  HAL
• 29 miscC.Carlos Pinzón, S.Santiago Quintero, S.Sergio Ramírez, C.Camilo Rueda and F.Frank Valencia. Counting and Computing Join-Endomorphisms in Lattices (Revisited).July 2022
  HAL
• 30 miscS.Santiago Quintero, C.Carlos Pinzón, S.Sergio Ramírez and F.Frank Valencia. On the Computation of Distributed Knowledge as the Greatest Lower Bound of Knowledge.August 2022
  HAL
• 31 miscS.Sebastian Simon, C.Cezara Petrui, C.Carlos Pinzón and C.Catuscia Palamidessi. Minimizing Information Leakage under Padding Constraints.December 2022
  HAL