Unité
Laboratoire d'ingéniérie de sécurité et privacy
LaboratoirePublications associées (112)
Differentially private multi-agent constraint optimization
Boi Faltings, Sujit Prakash Gujar, Aleksei Triastcyn, Sankarshan Damle
Distributed constraint optimization (DCOP) is a framework in which multiple agents with private constraints (or preferences) cooperate to achieve a common goal optimally. DCOPs are applicable in several multi-agent coordination/allocation problems, such as ...
Dordrecht2024Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning
Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...
EPFL2024A Privacy-Preserving Querying Mechanism with High Utility for Electric Vehicles
Electric vehicles (EVs) are becoming more popular due to environmental consciousness. The limited availability of charging stations (CSs), compared to the number of EVs on the road, has led to increased range anxiety and a higher frequency of CS queries du ...
Piscataway2024An Ultra-High Throughput AES-Based Authenticated Encryption Scheme for 6G: Design and Implementation
Andrea Felice Caforio, Subhadeep Banik
In this paper, we propose Rocca-S, an authenticated encryption scheme with a 256-bit key and a 256-bit tag targeting 6G applications bootstrapped from AES. Rocca-S achieves an encryption/decryption speed of more than 200 Gbps in the latest software environ ...
Springer International Publishing Ag2024Bridging the gap between theoretical and practical privacy technologies for at-risk populations
With the pervasive digitalization of modern life, we benefit from efficient access to information and services. Yet, this digitalization poses severe privacy challenges, especially for special-needs individuals. Beyond being a fundamental human right, priv ...
EPFL2023Arbitrary Decisions are a Hidden Cost of Differentially Private Training
Carmela González Troncoso, Bogdan Kulynych
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data (e.g., adding Ga ...
New York2023Challenging the Assumptions: Rethinking Privacy, Bias, and Security in Machine Learning
Predictive models based on machine learning (ML) offer a compelling promise: bringing clarity and structure to complex natural and social environments. However, the use of ML poses substantial risks related to the privacy of their training data as well as ...
EPFL2023On the (In)security of Peer-to-Peer Decentralized Machine Learning
Carmela González Troncoso, Mathilde Aliénor Raynal, Dario Pasquini
In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning-a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and ...
IEEE COMPUTER SOC2023Not Yet Another Digital ID: Privacy-Preserving Humanitarian Aid Distribution
Carmela González Troncoso, Boya Wang, Wouter Lueks, Justinas Sukaitis
Humanitarian aid-distribution programs help bring physical goods to people in need. Traditional paper-based solutions to support aid distribution do not scale to large populations and are hard to secure. Existing digital solutions solve these issues, at th ...
IEEE COMPUTER SOC2023Thwarting Malicious Adversaries in Homomorphic Encryption Pipelines
Homomorphic Encryption (HE) enables computations to be executed directly on encrypted data. As such, it is an auspicious solution for protecting the confidentiality of sensitive data without impeding its usability. However, HE does not provide any guarante ...
EPFL2023