{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:30:49Z","timestamp":1774539049391,"version":"3.50.1"},"reference-count":110,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/sp46215.2023.10179468","type":"proceedings-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T17:18:15Z","timestamp":1689959895000},"page":"1961-1979","source":"Crossref","is-referenced-by-count":87,"title":["ELSA: Secure Aggregation for Federated Learning with Malicious Actors"],"prefix":"10.1109","author":[{"given":"Mayank","family":"Rathee","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Conghao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Sameer","family":"Wagh","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Raluca Ada","family":"Popa","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]}],"member":"263","reference":[{"key":"ref7","article-title":"Emp toolkit"},{"key":"ref8","article-title":"Exposure notification privacy-preserving analytics (enpa) white paper"},{"key":"ref9","article-title":"Federated learning: Collaborative machine learning without centralized training data"},{"key":"ref10","article-title":"libprio-rs"},{"key":"ref11","article-title":"PETs Prize Challenge: Phase 2 (Financial Crime)"},{"key":"ref12","article-title":"PETs Prize Challenge: Phase 2 (Pandemic Forecasting)"},{"key":"ref13","article-title":"Prio+: Privacy Preserving Aggregate Statistics via Boolean Shares","author":"Addanki","year":"2021","journal-title":"IACR ePrint Archive 2021\/576"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978331"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516738"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516738"},{"key":"ref17","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"NeurIPS","author":"Baruch"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46766-1_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40084-1_6"},{"key":"ref21","article-title":"Protection against reconstruction and its applications in private federated learning","volume-title":"CoRR","author":"Bhowmick"},{"key":"ref22","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"NeurIPS","author":"Blanchard"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3335741.3335757"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/EuroSP57164.2023.00020","article-title":"When the curious abandon honesty: Federated learning is not private","volume-title":"CoRR","author":"Boenisch"},{"key":"ref25","article-title":"Towards federated learning at scale: System design","volume-title":"MLSys","author":"Bonawitz"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26954-8_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77886-6_30"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354255"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26954-8_16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363227"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00020"},{"key":"ref34","article-title":"Rofl: Attestable robustness for secure federated learning","volume-title":"CoRR","author":"Burkhalter"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422562"},{"key":"ref36","article-title":"LEAF: A benchmark for federated settings","volume-title":"CoRR","author":"Caldas"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96878-0_2"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1145\/3548606.3560611","article-title":"Eiffel: Ensuring integrity for federated learning","volume-title":"CoRR","author":"Chowdhury"},{"key":"ref41","article-title":"Prio: Private, robust, and scalable computation of aggregate statistics","volume-title":"NSDI","author":"Corrigan-Gibbs"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.27"},{"key":"ref43","article-title":"SPDZ2k: Efficient MPC mod 2k for dishonest majority","volume-title":"CRYPTO","author":"Cramer"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00078"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32009-5_38"},{"key":"ref46","article-title":"DORY: an encrypted search system with distributed trust","volume-title":"USENIX ODSI","author":"Dauterman"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833611"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2015.23113"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660280"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-56880-1_29"},{"key":"ref52","article-title":"Express: Lowering the cost of metadata-hiding communication with cryptographic privacy","volume-title":"USENIX Security","author":"Eskandarian"},{"key":"ref53","article-title":"Local model poisoning attacks to byzantine-robust federated learning","volume-title":"USENIX Security","author":"Fang"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-47721-7_12","article-title":"How to prove yourself: Practical solutions to identification and signature problems","volume-title":"CRYPTO \u201986","author":"Fiat"},{"key":"ref55","doi-asserted-by":"crossref","DOI":"10.1109\/TII.2020.3036166","article-title":"VFL: A verifiable federated learning with privacy-preserving for big data in industrial iot","volume-title":"CoRR","author":"Fu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38348-9_37"},{"key":"ref57","article-title":"Differentially private federated learning: A client level perspective","volume-title":"CoRR","author":"Geyer"},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.1145\/3335741.3335755","article-title":"How to Play any Mental Game or A Completeness Theorem for Protocols with Honest Majority","volume-title":"ACM STOC","author":"Goldreich"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-56880-1_28"},{"key":"ref60","article-title":"Scalable and private media consumption with popcorn","volume-title":"13th USENIX NSDI","author":"Gupta"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3488014"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761267"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"Secure byzantine-robust machine learning","volume-title":"CoRR","author":"He"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2931068"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00076"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45146-4_9"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3302505.3310070"},{"key":"ref70","article-title":"Fastsecagg: Scalable secure aggregation for privacy-preserving federated learning","volume-title":"CoRR","author":"Kadhe"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-47989-6_35"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978357"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78372-7_6"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40084-1_4"},{"key":"ref76","article-title":"Federated learning: Strategies for improving communication efficiency","volume-title":"CoRR","author":"Kone\u0107n\u00fd"},{"key":"ref77","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00092"},{"key":"ref79","article-title":"Adversarial machine learning-industry perspectives","volume-title":"SP Workshops","author":"Kumar"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57048-8_6"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00017"},{"key":"ref83","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"AISTATS","author":"McMahan"},{"key":"ref84","article-title":"The hidden vulnerability of distributed learning in byzantium","volume-title":"ICML","author":"Mhamdi"},{"key":"ref85","article-title":"Aby3: A mixed protocol framework for machine learning","volume-title":"CCS","author":"Mohassel"},{"key":"ref86","article-title":"Efficient oblivious transfer protocols","volume-title":"SODA","author":"Naor"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32009-5_40"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3153135"},{"key":"ref89","article-title":"Senate: A maliciously-secure MPC platform for collaborative analytics","volume-title":"USENIX Security","author":"Poddar"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00086"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417274"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31578-8_19"},{"key":"ref93","article-title":"Elsa: Secure aggregation for federated learning with malicious actors","author":"Rathee","year":"2022","journal-title":"IACR ePrint Archive 2022\/1695"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35423-7_12"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363228"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359176"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref100","doi-asserted-by":"crossref","DOI":"10.1109\/SP46214.2022.9833647","article-title":"Back to the drawing board: A critical evaluation of poisoning attacks on federated learning","volume-title":"CoRR","author":"Shejwalkar"},{"key":"ref101","article-title":"Privacy-preserving aggregation of time-series data","volume-title":"NDSS","author":"Shi"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041404"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3054610"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1080\/0025570X.1996.11996456"},{"key":"ref105","article-title":"Can you really backdoor federated learning?","volume-title":"CoRR","author":"Sun"},{"key":"ref106","article-title":"Distributed mean estimation with limited communication","volume-title":"ICML","author":"Suresh"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281252"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s00287-019-01205-x"},{"key":"ref109","article-title":"Splinter: Practical private queries on public data","volume-title":"NSDI","author":"Wang"},{"key":"ref110","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"NeurIPS","author":"Wang"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2929409"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357371"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417276"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/sfcs.1986.25"},{"key":"ref115","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"ICML","author":"Yin"},{"key":"ref116","article-title":"Batchcrypt: Efficient homomorphic encryption for cross-silo federated learning","volume-title":"USENIX ATC","author":"Zhang"}],"event":{"name":"2023 IEEE Symposium on Security and Privacy (SP)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,5,21]]},"end":{"date-parts":[[2023,5,25]]}},"container-title":["2023 IEEE Symposium on Security and Privacy (SP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10179215\/10179280\/10179468.pdf?arnumber=10179468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T05:12:18Z","timestamp":1721452338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10179468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":110,"URL":"https:\/\/doi.org\/10.1109\/sp46215.2023.10179468","relation":{},"subject":[],"published":{"date-parts":[[2023,5]]}}}