162 citations · 883 across the 43 of their papers we have counts for
45 papers
Security and Privacy in Agentic AI: Grand Challenges and Future Directions
Adam Jenkins, Agnieszka Kitkowska, Caterina Maidhof +22
We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading intern…
How to Get Actual Privacy and Utility from Privacy Models: the k-Anonymity and Differential Privacy Families
Josep Domingo-Ferrer, David Sánchez
Privacy models were introduced in privacy-preserving data publishing and statistical disclosure control with the promise to end the need for costly empirical assessment of disclosu…
Efficient Unlearning with Privacy Guarantees
Josep Domingo-Ferrer, Najeeb Jebreel, David Sánchez
Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML)…
A Consensus Privacy Metrics Framework for Synthetic Data
Lisa Pilgram, Fida K. Dankar, Jorg Drechsler +12
Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals' privacy…
Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
Alberto Blanco-Justicia, Najeeb Jebreel, Benet Manzanares +4
The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations fo…
Conciliating Privacy and Utility in Data Releases via Individual Differential Privacy and Microaggregation
Jordi Soria-Comas, David Sánchez, Josep Domingo-Ferrer +2
-Differential privacy (DP) is a well-known privacy model that offers strong privacy guarantees. However, when applied to data releases, DP significantly deteriorates the analyti…
Multi-Task Faces (MTF) Data Set: A Legally and Ethically Compliant Collection of Face Images for Various Classification Tasks
Rami Haffar, David Sánchez, Josep Domingo-Ferrer
Human facial data offers valuable potential for tackling classification problems, including face recognition, age estimation, gender identification, emotion analysis, and race clas…
An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdata
David Sánchez, Najeeb Jebreel, Krishnamurty Muralidhar +2
The threat of reconstruction attacks has led the U.S. Census Bureau (USCB) to replace in the Decennial Census 2020 the traditional statistical disclosure limitation based on rank s…
Defending Against Backdoor Attacks by Layer-wise Feature Analysis
Najeeb Moharram Jebreel, Josep Domingo-Ferrer, Yiming Li
Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third pa…
Database Reconstruction Is Not So Easy and Is Different from Reidentification
Krishnamurty Muralidhar, Josep Domingo-Ferrer
In recent years, it has been claimed that releasing accurate statistical information on a database is likely to allow its complete reconstruction. Differential privacy has been sug…
GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
Emily Jefferson, James Liley, Maeve Malone +16
TREs are widely, and increasingly used to support statistical analysis of sensitive data across a range of sectors (e.g., health, police, tax and education) as they enable secure a…
Bistochastic privacy
Nicolas Ruiz, Josep Domingo-Ferrer
We introduce a new privacy model relying on bistochastic matrices, that is, matrices whose components are nonnegative and sum to 1 both row-wise and column-wise. This class of matr…
Defending against the Label-flipping Attack in Federated Learning
Najeeb Moharram Jebreel, Josep Domingo-Ferrer, David Sánchez +1
Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in th…
A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
Alberto Blanco-Justicia, David Sanchez, Josep Domingo-Ferrer +1
We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP…
FL-Defender: Combating Targeted Attacks in Federated Learning
Najeeb Jebreel, Josep Domingo-Ferrer
Federated learning (FL) enables learning a global machine learning model from local data distributed among a set of participating workers. This makes it possible i) to train more a…
Enhanced Security and Privacy via Fragmented Federated Learning
Najeeb Moharram Jebreel, Josep Domingo-Ferrer, Alberto Blanco-Justicia +1
In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconcili…
Circuit-Free General-Purpose Multi-Party Computation via Co-Utile Unlinkable Outsourcing
Josep Domingo-Ferrer, Jesús Manjón
Multiparty computation (MPC) consists in several parties engaging in joint computation in such a way that each party's input and output remain private to that party. Whereas MPC pr…
Secure and Privacy-Preserving Federated Learning via Co-Utility
Josep Domingo-Ferrer, Alberto Blanco-Justicia, Jesús Manjón +1
The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a…
Achieving Security and Privacy in Federated Learning Systems: Survey, Research Challenges and Future Directions
Alberto Blanco-Justicia, Josep Domingo-Ferrer, Sergio Martínez +3
Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with…
The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)
Josep Domingo-Ferrer, David Sánchez, Alberto Blanco-Justicia
Differential privacy (DP) is a neat privacy definition that can co-exist with certain well-defined data uses in the context of interactive queries. However, DP is neither a silver…
General Confidentiality and Utility Metrics for Privacy-Preserving Data Publishing Based on the Permutation Model
Josep Domingo-Ferrer, Krishnamurty Muralidhar, Maria Bras-Amorós
Anonymization for privacy-preserving data publishing, also known as statistical disclosure control (SDC), can be viewed under the lens of the permutation model. According to this m…
Multi-Dimensional Randomized Response
Josep Domingo-Ferrer, Jordi Soria-Comas
In our data world, a host of not necessarily trusted controllers gather data on individual subjects. To preserve her privacy and, more generally, her informational self-determinati…
Give more data, awareness and control to individual citizens, and they will help COVID-19 containment
Mirco Nanni, Gennady Andrienko, Albert-László Barabási +36
The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the phase 2 of the pandemic, when…
The future of statistical disclosure control
Mark Elliot, Josep Domingo-Ferrer
Statistical disclosure control (SDC) was not created in a single seminal paper nor following the invention of a new mathematical technique, rather it developed slowly in response t…