Follow
Eugene Bagdasaryan
Eugene Bagdasaryan
Cornell Tech, Google
Verified email at cornell.edu - Homepage
Title
Cited by
Cited by
Year
How to backdoor federated learning
E Bagdasaryan, A Veit, Y Hua, D Estrin, V Shmatikov
International conference on artificial intelligence and statistics, 2938-2948, 2020
17502020
Differential privacy has disparate impact on model accuracy
E Bagdasaryan, O Poursaeed, V Shmatikov
Advances in neural information processing systems 32, 2019
4532019
Salvaging federated learning by local adaptation
T Yu, E Bagdasaryan, V Shmatikov
arXiv preprint arXiv:2002.04758, 2020
2622020
Blind backdoors in deep learning models
E Bagdasaryan, V Shmatikov
30th USENIX Security Symposium (USENIX Security 21), 1505-1521, 2021
2612021
X-containers: Breaking down barriers to improve performance and isolation of cloud-native containers
Z Shen, Z Sun, GE Sela, E Bagdasaryan, C Delimitrou, R Van Renesse, ...
Proceedings of the Twenty-Fourth International Conference on Architectural …, 2019
852019
Openrec: A modular framework for extensible and adaptable recommendation algorithms
L Yang, E Bagdasaryan, J Gruenstein, CK Hsieh, D Estrin
Proceedings of the Eleventh ACM International Conference on Web Search and …, 2018
682018
Spinning language models: Risks of propaganda-as-a-service and countermeasures
E Bagdasaryan, V Shmatikov
2022 IEEE Symposium on Security and Privacy (SP), 769-786, 2022
67*2022
Ancile: Enhancing privacy for ubiquitous computing with use-based privacy
E Bagdasaryan, G Berlstein, J Waterman, E Birrell, N Foster, ...
Proceedings of the 18th ACM Workshop on Privacy in the Electronic Society …, 2019
262019
Towards sparse federated analytics: Location heatmaps under distributed differential privacy with secure aggregation
E Bagdasaryan, P Kairouz, S Mellem, A Gascón, K Bonawitz, D Estrin, ...
Proceedings on Privacy Enhancing Technologies 2022 (4), 162–182, 2022
202022
Derecho: Group communication at the speed of light
J Behrens, K Birman, S Jha, M Milano, E Tremel, E Bagdasaryan, ...
Technical Report. Cornell University, 2016
162016
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
E Bagdasaryan, TY Hsieh, B Nassi, V Shmatikov
arXiv preprint arXiv:2307.10490 3, 2023
102023
Policy-based federated learning
K Katevas, E Bagdasaryan, J Waterman, MM Safadieh, E Birrell, ...
arXiv preprint arXiv:2003.06612, 2020
42020
Training a Tokenizer for Free with Private Federated Learning
E Bagdasaryan, C Song, R van Dalen, M Seigel, Á Cahill
ACL FL4NLP, 2022
22022
Modularizing deep neural network-inspired recommendation algorithms
L Yang, E Bagdasaryan, H Wen
Proceedings of the 12th ACM Conference on Recommender Systems, 533-534, 2018
22018
Ceci n'est pas une pomme: Adversarial Illusions in Multi-Modal Embeddings
E Bagdasaryan, V Shmatikov
arXiv preprint arXiv:2308.11804, 2023
12023
Mithridates: Boosting Natural Resistance to Backdoor Learning
E Bagdasaryan, V Shmatikov
arXiv preprint arXiv:2302.04977, 2023
1*2023
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models
SJ Yang, CD La, QH Nguyen, E Bagdasaryan, KS Wong, AT Tran, ...
arXiv preprint arXiv:2312.03419, 2023
2023
Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines
E Bagdasaryan, V Shmatikov
arXiv preprint arXiv:2302.04977, 2023
2023
(Un) Trustworthy Machine Learning
E Bagdasaryan
Cornell University, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–19