Exploiting unintended feature leakage in collaborative learning L Melis, C Song, E De Cristofaro, V Shmatikov 2019 IEEE symposium on security and privacy (SP), 691-706, 2019 | 1954 | 2019 |
Logan: Membership inference attacks against generative models J Hayes, L Melis, G Danezis, E De Cristofaro arXiv preprint arXiv:1705.07663, 2017 | 724* | 2017 |
Differentially private mixture of generative neural networks G Acs, L Melis, C Castelluccia, E De Cristofaro IEEE Transactions on Knowledge and Data Engineering 31 (6), 1109-1121, 2018 | 172 | 2018 |
Efficient private statistics with succinct sketches L Melis, G Danezis, E De Cristofaro NDSS 2016, 2015 | 162 | 2015 |
Differentially private query release through adaptive projection S Aydore, W Brown, M Kearns, K Kenthapadi, L Melis, A Roth, AA Siva International Conference on Machine Learning, 457-467, 2021 | 86 | 2021 |
Splitbox: Toward efficient private network function virtualization HJ Asghar, L Melis, C Soldani, E De Cristofaro, MA Kaafar, L Mathy Proceedings of the 2016 workshop on Hot topics in Middleboxes and Network …, 2016 | 52 | 2016 |
Private processing of outsourced network functions: Feasibility and constructions L Melis, HJ Asghar, E De Cristofaro, MA Kaafar Proceedings of the 2016 ACM International Workshop on Security in Software …, 2016 | 39 | 2016 |
Adversarial robustness with non-uniform perturbations E Erdemir, J Bickford, L Melis, S Aydore Advances in Neural Information Processing Systems 34, 19147-19159, 2021 | 33 | 2021 |
Towards fair federated recommendation learning: Characterizing the inter-dependence of system and data heterogeneity K Maeng, H Lu, L Melis, J Nguyen, M Rabbat, CJ Wu Proceedings of the 16th ACM Conference on Recommender Systems, 156-167, 2022 | 32 | 2022 |
Federated linear contextual bandits with user-level differential privacy R Huang, H Zhang, L Melis, M Shen, M Hejazinia, J Yang International Conference on Machine Learning, 14060-14095, 2023 | 15 | 2023 |
Measuring and Privately Building Highly Predictive Blacklisting L Melis, A Pyrgelis, E De Cristofaro | 15* | |
Detecting anomalous events using autoencoders B Coskun, W Ding, L Melis US Patent 11,374,952, 2022 | 12 | 2022 |
Have Missing Data? Make It Miss More! Imputing Tabular Data with Masked Autoencoding T Du, L Melis, T Wang | 10* | |
Federated Ensemble Learning: Increasing the Capacity of Label Private Recommendation Systems. M Hejazinia, D Huba, I Leontiadis, K Maeng, M Malek, L Melis, I Mironov, ... IEEE Data Eng. Bull. 46 (1), 145-157, 2023 | 7* | 2023 |
Noisy Neighbors: Efficient membership inference attacks against LLMs F Galli, L Melis, T Cucinotta arXiv preprint arXiv:2406.16565, 2024 | 5 | 2024 |
EXACT: Extensive Attack for Split Learning X Qiu, I Leontiadis, L Melis, A Sablayrolles, P Stock arXiv preprint arXiv:2305.12997, 2023 | 4 | 2023 |
Detecting anomalous events from categorical data using autoencoders S Aydore, B Coskun, L Melis US Patent 11,537,902, 2022 | 3 | 2022 |
Auditing -Differential Privacy in One Run S Mahloujifar, L Melis, K Chaudhuri arXiv preprint arXiv:2410.22235, 2024 | 2 | 2024 |
Building and evaluating privacy-preserving data processing systems L Melis UCL (University College London), 2018 | 2 | 2018 |
Fast privacy-preserving network function outsourcing HJ Asghar, E De Cristofaro, G Jourjon, MA Kaafar, L Mathy, L Melis, ... Computer Networks 163, 106893, 2019 | 1 | 2019 |