Sustainable & Resilient Societies

Humanity is facing unprecedented challenges driven by climate change. As we cannot only count on technological solutions, people must be incentivized to contribute to more resilient and sustainable societies.

Designing and adapting artificial intelligence models to include people can help us to take on these challenges. With their multidisciplinary expertise, Idiap researchers can help to include this human dimension. Their work contributes to tackling misinformation while reducing energy costs, and to identifying relevant social trends while helping us to understand our environment.

Expertise domains



This program contributes to the following UN SDG



There was an error while rendering this tile


Publication highlights

Integrating daylight with general and task lighting: A longitudinal in-the-wild study in individual and open space working areas, Chantal Basurto, Michael Papinutto, Moreno Colombo, Roberto Boghetti, Kornelius Reutter, Julien Nembrini and Jérôme Kämpf, in: Solar Energy Advances, 2, 2022

This paper makes use of AI-based surrogate models to predict the indoor lighting conditions and control optimally the blinds and electric lighting to maintain visual comfort and achieve energy savings. More than 50% of electricity for lighting were saved without impacting significantly visual comfort over the course of our longitudinal experiment.


Comprehensive Vulnerability Evaluation of Face Recognition Systems to Template Inversion Attacks Via 3D Face Reconstruction, H. S. Otroshi and S. Marcel, IEEE TPAMI 2023, DOI ( )

In this work, we propose a new method (called GaFaR) to reconstruct 3D faces from facial templates using a pretrained geometry-aware face generation network, and train a mapping from facial templates to the intermediate latent space of the face generator network. We train our mapping with a semi-supervised approach using real and synthetic face images. For real face images, we use a generative adversarial network (GAN)-based framework to learn the distribution of generator intermediate latent space. For synthetic face images, we directly learn the mapping from facial templates to the generator intermediate latent code. We demonstrated the transferability of our attack with state-of-the-art methods across other face recognition systems. We also performed practical presentation attacks on face recognition systems using the digital screen replay and printed photographs, and evaluated the vulnerability of face recognition systems to different template inversion attacks.


Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction, Martin Fajcik, Petr Motlicek and Pavel Smrz, in: Association for Computational Linguistics, Findings of the Association for Computational Linguistics: ACL 2023:10184–10205, 2023.

This paper describes new latent variable model for fact-checking and fact-analysis, which given a claim and a set of retrieved provenances allows learning jointly: (i) what are the relevant provenances to this claim (ii) what is the veracity of this claim. We propose to disentangle the per-provenance relevance probability and its contribution to the final veracity probability in an interpretable way - the final veracity probability is proportional to a linear ensemble of per-provenance relevance probabilities. This way, it can be clearly identified the relevance of which sources contributes to what extent towards the final probability. We show that our system achieves state-of-the-art results on FEVER dataset comparable to two-stage systems typically used in traditional fact-checking pipelines, while it often uses significantly less parameters and computation.

Project highlights

Eguzki, 2020-2024, SFOE, KÄMPF: A simulation program for district heating networks based on artificial intelligence for the rapid and predictive resolution of complex looped networks

The project focuses on the pivotal role of district heating networks in harnessing lost heat for energy efficiency. It uses artificial intelligence to optimize network design, reduce costs, and minimize energy losses before significant investments are made.


TRESPASS, 2020-2024, H2020, MARCEL: Biometrics security and privacy preservation

The aim of this project is to combat rising security challenges with biometric technologies which are growing at a fast pace. More particularly, our researchers are investigating new types of security protection (e.g. presentation attack detection (PAD), morphing attack detection (MAD), deepfake detection (DD) or poisoning detection technologies) and privacy preservation (e.g. vulnerability assessment, template protection or computationally feasible encryption solutions).


CRiTERIA, 2021-2024, H2020, MOTLICEK: Comprehensive data-driven Risk and Threat Assessment Methods for the Early and Reliable Identification, Validation and Analysis of migration-related risks

The project aims to strengthen and expand existing risk analysis methods by introducing a novel, comprehensive but feasible and human-rights sensitive risk and vulnerability analysis framework for border agencies. The project started in 2021 and runs for three years. Idiap contributes to the project by developing innovative solutions automatically extracting relevant evidence from spoken and textual resources. Among technologies developed by Idiap are: (a) multilingual automatic speech recognition, (b) fact-checking system (i.e., system which can verify a claim formulated in natural language, whether it is true or not, by confirming against other factoid sources, and (c) reliability detector (i.e., a tool which can automatically evaluate the reliability of source (related to general OSINT data) as an unavoidable block for the fact-checking system.

Full list of related projects

Eguzki and IVECT, 2020-2023, SFOE, Kämpf

Built environment sustainability


SOTERIA, 2022-2024, EU, Marcel

Face recognition anti-spoofing


GRAIL, 2022-2025, US IARPA, Marcel

Person recognition at a distance


TRESPASS, 2020-2024, EU, Marcel

Biometrics security and privacy preservation


CRiTERIA, 2021-2024, EU, Motlicek

Comprehensive data-driven risk and threat assessment methods for the early and reliable Identification, validation and analysis of migration-related risks


ROXANNE, 2019-2023, EU, Motlicek

Real-time network, text and speaker analytics for combating organized crime


TRACY, 2023-2025, EU, Motlicek

Big-data analytics from base-stations registrations and e-evidence system