Antonio Fernández Anta

Antonio Russo, Antonio Fernández Anta, Maria Isabel González Vasco et al.

In this paper we propose a comprehensive and scalable framework to build secure-by-design e-voting systems. Decentralization, transparency, determinism, and untamperability of votes are granted by dedicated smart contracts on a blockchain, while voter authenticity and anonymity are achieved through (provable secure) linkable ring signatures. These, in combination with suitable smart contract constraints, also grant protection from double voting. Our design is presented in detail, focusing on its security guarantees and the design choices that allow it to scale to a large number of voters. Finally, we present a proof-of-concept implementation of the proposed framework, made available as open source.

Ahmad Khalil, Tizian Dege, Pegah Golchin et al.

In the pursuit of refining precise perception models for fully autonomous driving, continual online model training becomes essential. Federated Learning (FL) within vehicular networks offers an efficient mechanism for model training while preserving raw sensory data integrity. Yet, FL struggles with non-identically distributed data (e.g., quantity skew), leading to suboptimal convergence rates during model training. In previous work, we introduced FedLA, an innovative Label-Aware aggregation method addressing data heterogeneity in FL for generic scenarios. In this paper, we introduce FedProx+LA, a novel FL method building upon the state-of-the-art FedProx and FedLA to tackle data heterogeneity, which is specifically tailored for vehicular networks. We evaluate the efficacy of FedProx+LA in continuous online object detection model training. Through a comparative analysis against conventional and state-of-the-art methods, our findings reveal the superior convergence rate of FedProx+LA. Notably, if the label distribution is very heterogeneous, our FedProx+LA approach shows substantial improvements in detection performance compared to baseline methods, also outperforming our previous FedLA approach. Moreover, both FedLA and FedProx+LA increase convergence speed by 30% compared to baseline methods.

Tobias Meuser, Oluwasegun Taiwo Ojo, Daniel Bischoff et al.

To support location-based services, vehicles must share their location with a server to receive relevant data, compromising their (location) privacy. To alleviate this privacy compromise, the vehicle's location can be obfuscated by adding artificial noise. Under limited available bandwidth, and since the area including the vehicle's location increases with the noise, the server will provide fewer data relevant to the vehicle's true location, reducing the effectiveness of a location-based service. To alleviate this problem, we propose that data relevant to a vehicle is also provided through direct, ad hoc communication by neighboring vehicles. Through such Vehicle-to-Vehicle (V2V) cooperation, the impact of location obfuscation is mitigated. Since vehicles subscribe to data of (location-dependent) impact values, neighboring vehicles will subscribe to largely overlapping sets of data, reducing the benefit of V2V cooperation. To increase such benefit, we develop and study a non-cooperative game determining the data that a vehicle should subscribe to, aiming at maximizing its utilization while considering the participating (neighboring) vehicles. Our analysis and results show that the proposed V2V cooperation and derived strategy lead to significant performance increase compared to non-cooperative approaches and largely alleviates the impact of privacy on location-based services.

Rafael Garcia Leiva, Antonio Fernandez Anta, Vincenzo Mancuso et al.

Decision trees are an extremely popular machine learning technique. Unfortunately, overfitting in decision trees still remains an open issue that sometimes prevents achieving good performance. In this work, we present a novel approach for the construction of decision trees that avoids the overfitting by design, without losing accuracy. A distinctive feature of our algorithm is that it requires neither the optimization of any hyperparameters, nor the use of regularization techniques, thus significantly reducing the decision tree training time. Moreover, our algorithm produces much smaller and shallower trees than traditional algorithms, facilitating the interpretability of the resulting models.

Manuel Alfonseca, Manuel Cebrian, Antonio Fernandez Anta et al.

Superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. In light of recent advances in machine intelligence, a number of scientists, philosophers and technologists have revived the discussion about the potential catastrophic risks entailed by such an entity. In this article, we trace the origins and development of the neo-fear of superintelligence, and some of the major proposals for its containment. We argue that such containment is, in principle, impossible, due to fundamental limits inherent to computing itself. Assuming that a superintelligence will contain a program that includes all the programs that can be executed by a universal Turing machine on input potentially as complex as the state of the world, strict containment requires simulations of such a program, something theoretically (and practically) infeasible.