@article{MTMT:34686117,
	title = {A Secure Federated Data-Driven Evolutionary Multi-Objective Optimization Algorithm},
	url = {https://m2.mtmt.hu/api/publication/34686117},
	author = {Liu, Q. and Yan, Y. and Ligeti, P. and Jin, Y. and Yan, Yuping and Ligeti, Péter},
	doi = {10.1109/TETCI.2023.3313555},
	journal-iso = {IEEE TRANS EMERG TOPIC COMPUT INTELL},
	journal = {IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE},
	volume = {8},
	unique-id = {34686117},
	issn = {2471-285X},
	abstract = {Data-driven evolutionary algorithms usually aim to exploit the information behind a limited amount of data to perform optimization, which have proved to be successful in solving many complex real-world optimization problems. However, most data-driven evolutionary algorithms are centralized, causing privacy and security concerns. Existing federated Bayesian optimization algorithms and data-driven evolutionary algorithms mainly protect the raw data on each client. To address this issue, this article proposes a secure federated data-driven evolutionary multi-objective optimization algorithm to protect both the raw data and the newly infilled solutions obtained by optimizing the acquisition function conducted on the server. We select the query points on a randomly selected client at each round of surrogate update by calculating the acquisition function values of the unobserved points on this client, thereby reducing the risk of leaking the information about the solution to be sampled. In addition, since the predicted objective values of each client may contain sensitive information, we mask the objective values with Diffie-Hellman-based noise, and then send only the masked objective values of other clients to the selected client via the server. Since the calculation of the acquisition function also requires both the predicted objective value and the uncertainty of the prediction, the predicted mean objective and uncertainty are normalized to reduce the influence of noise. Experimental results on a set of widely used multi-objective optimization benchmarks show that the proposed algorithm can protect privacy and enhance security with only negligible sacrifice in the performance of federated data-driven evolutionary optimization. © 2017 IEEE.},
	keywords = {Evolutionary algorithms; job analysis; Optimisations; Multiobjective optimization; Benchmarking; Privacy; BAYES METHOD; Task analysis; Privacy preserving; privacy-preserving; Evolutionary Multi-objective optimization; Evolutionary multiobjective optimization; Bayesian optimization; Data driven; Privacy-preserving techniques; Diffie Hellman; data-driven evolutionary algorithm; Diffie-Hellman; federated Bayesian optimization; Data-driven evolutionary algorithm; Federated bayesian optimization},
	year = {2024},
	eissn = {2471-285X},
	pages = {191-205},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@article{MTMT:34429495,
	title = {Secure Federated Evolutionary Optimization—A Survey},
	url = {https://m2.mtmt.hu/api/publication/34429495},
	author = {Liu, Qiqi and Yan, Yuping and Jin, Yaochu and Wang, Xilu and Ligeti, Péter and Yu, Guo and Yan, Xueming},
	doi = {10.1016/j.eng.2023.10.006},
	journal-iso = {ENGINEERING-PRC},
	journal = {ENGINEERING},
	volume = {Available online 7 December 2023},
	unique-id = {34429495},
	issn = {2095-8099},
	year = {2024},
	eissn = {2096-0026},
	pages = {&},
	orcid-numbers = {Liu, Qiqi/0000-0003-1587-5515; Jin, Yaochu/0000-0003-1100-0631; Wang, Xilu/0000-0002-0926-4454; Ligeti, Péter/0000-0002-3998-0515; Yu, Guo/0000-0003-2427-8202}
}

@article{MTMT:34087599,
	title = {Fedlabx: a practical and privacy-preserving framework for federated learning},
	url = {https://m2.mtmt.hu/api/publication/34087599},
	author = {Yan, Yuping and Albujeer, Mohammed B. M. Kamel and Zoltay, Marcell and Gál, Marcell and Hollós, Roland and Jin, Yaochu and Ligeti, Péter and Tényi, Ákos},
	doi = {10.1007/s40747-023-01184-3},
	journal-iso = {COMPLEX INTELL SYST},
	journal = {COMPLEX & INTELLIGENT SYSTEMS},
	volume = {10},
	unique-id = {34087599},
	issn = {2199-4536},
	abstract = {Federated learning (FL) draws attention in academia and industry due to its privacy-preserving capability in training machine learning models. However, there are still some critical security attacks and vulnerabilities, including gradients leakage and interference attacks. Meanwhile, communication is another bottleneck in basic FL schemes since large-scale FL parameter transmission leads to inefficient communication, latency, and slower learning processes. To overcome these shortcomings, different communication efficiency strategies and privacy-preserving cryptographic techniques have been proposed. However, a single method can only partially resist privacy attacks. This paper presents a practical, privacy-preserving scheme combining cryptographic techniques and communication networking solutions. We implement Kafka for message distribution, the Diffie–Hellman scheme for secure server aggregation, and gradient differential privacy for interference attack prevention. The proposed approach maintains training efficiency while being able to addressing gradients leakage problems and interference attacks. Meanwhile, the implementation of Kafka and Zookeeper provides asynchronous communication and anonymous authenticated computation with role-based access controls. Finally, we prove the privacy-preserving properties of the proposed solution via security analysis and empirically demonstrate its efficiency and practicality.},
	year = {2023},
	eissn = {2198-6053},
	pages = {677-690},
	orcid-numbers = {Jin, Yaochu/0000-0003-1100-0631; Ligeti, Péter/0000-0002-3998-0515}
}

@inproceedings{MTMT:33574975,
	title = {A Survey of Personalized and Incentive Mechanisms for Federated Learning},
	url = {https://m2.mtmt.hu/api/publication/33574975},
	author = {Yan, Yuping and Ligeti, Péter},
	booktitle = {2022 IEEE 2nd Conference on Information Technology and Data Science (CITDS)},
	doi = {10.1109/CITDS54976.2022.9914268},
	unique-id = {33574975},
	year = {2022},
	pages = {324-329},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@inproceedings{MTMT:33550662,
	title = {Attribute Verifier for Internet of Things},
	url = {https://m2.mtmt.hu/api/publication/33550662},
	author = {Albujeer, Mohammed B. M. Kamel and Yan, Yuping and Ligeti, Péter and Reich, Christoph},
	booktitle = {2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)},
	doi = {10.1109/ITNAC55475.2022.9998348},
	unique-id = {33550662},
	abstract = {Identity management, authentication, and attribute verification are among the main concerns in many Internet of Things (IoT) applications. Considering the privacy concerns, attribute verification became more important in many applications. Many of the proposed models in this field suffer from privacy and scalability issues as they depend on a centralized entity. In this paper, we proposed a decentralized attribute verifier based on a challenge-response approach. To address various IoT attribute verification requirements, the proposed model provides two modes of attribute verification, namely 1-out-of-n verification and n-out-of-n verification modes, in which the participants can prove the possession of one or all of the given target attributes.},
	keywords = {attribute-based encryption; Zero-knowledge proof; attribute verification},
	year = {2022},
	pages = {320-322},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@inproceedings{MTMT:33140101,
	title = {Improving Security and Privacy in Attribute-Based Encryption with Anonymous Credential},
	url = {https://m2.mtmt.hu/api/publication/33140101},
	author = {Yan, Yuping and Ligeti, Péter},
	booktitle = {Recent Innovations in Computing},
	doi = {10.1007/978-981-16-8892-8_58},
	unique-id = {33140101},
	year = {2022},
	pages = {767-778},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@inproceedings{MTMT:33110250,
	title = {Security Verification of Key Exchange in Ciphertext-Policy Attribute Based Encryption},
	url = {https://m2.mtmt.hu/api/publication/33110250},
	author = {Bat-Erdene, Baasansuren and Yan, Yuping and Albujeer, Mohammed B. M. Kamel and Ligeti, Péter},
	booktitle = {2022 7th International Conference on Signal and Image Processing (ICSIP)},
	doi = {10.1109/ICSIP55141.2022.9887218},
	unique-id = {33110250},
	year = {2022},
	pages = {377-381},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@CONFERENCE{MTMT:32246282,
	title = {Formal Verification of Confidentiality in Attribute-Based Encryption through ProVerif},
	url = {https://m2.mtmt.hu/api/publication/32246282},
	author = {Erdenebat, Baasanjargal and Yan, Yuping and Albujeer, Mohammed B. M. Kamel},
	booktitle = {Book of Abstracts: 21th Central European Conference on Cryptology},
	unique-id = {32246282},
	year = {2021},
	pages = {34-35}
}

@article{MTMT:32154507,
	title = {Attred: Attribute Based Resource Discovery for IoT},
	url = {https://m2.mtmt.hu/api/publication/32154507},
	author = {Albujeer, Mohammed B. M. Kamel and Yan, Yuping and Ligeti, Péter and Reich, Christoph},
	doi = {10.3390/s21144721},
	journal-iso = {SENSORS-BASEL},
	journal = {SENSORS},
	volume = {21},
	unique-id = {32154507},
	year = {2021},
	eissn = {1424-8220},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}

@misc{MTMT:32091534,
	title = {Improving Security and Privacy in Attribute-based Encryption with Anonymous Credential},
	url = {https://m2.mtmt.hu/api/publication/32091534},
	author = {Yan, Yuping and Ligeti, Péter},
	unique-id = {32091534},
	year = {2021},
	orcid-numbers = {Ligeti, Péter/0000-0002-3998-0515}
}