Acknowledgement
이 논문은 2024년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (RS-2023-00277326). 이 논문은 2023년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(IITP-2023-RS-2023-00256081). 이 논문은 2022년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (No. 2022-0-00516, 국가통계데이터에 적용 가능한 차등 정보보호 개념을 도출하고 통계분석의 유용성을 보장해야 하는 문제 해결). 이 논문은 2024년도 BK21 FOUR 정보기술 미래인재 교육연구단에 의하여 지원되었음. 본 연구는 반도체 공동연구소 지원의 결과물임을 밝힙니다.
References
- Lamport, Leslie, Robert Shostak, and Marshall Pease. "The Byzantine generals problem." Concurrency: the works of leslie lamport. 2019. 203-226.
- Fang, Minghong, et al. "Local model poisoning attacks to {Byzantine-Robust} federated learning." 29th USENIX security symposium (USENIX Security 20). 2020.
- Shejwalkar, Virat, and Amir Houmansadr. "Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning." NDSS. 2021.
- Lee, Younghan, et al. "FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models." European Symposium on Research in Computer Security. Cham: Springer Nature Switzerland, 2023.
- Li, Daliang, and Junpu Wang. "Fedmd: Heterogenous federated learning via model distillation." arXiv preprint arXiv:1910.03581 (2019).
- Takahashi, Hideaki, Jingjing Liu, and Yang Liu. "Breaching FedMD: image recovery via paired-logits inversion attack." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.
- Fang, Xiuwen, and Mang Ye. "Robust federated learning with noisy and heterogeneous clients." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
- Bagdasaryan, Eugene, et al. "How to backdoor federated learning." International conference on artificial intelligence and statistics. PMLR, 2020.
- Blanchard, Peva, et al. "Machine learning with adversaries: Byzantine tolerant gradient descent." Advances in neural information processing systems 30 (2017).
- Chaudhari, Harsh, et al. "SNAP: Efficient extraction of private properties with poisoning." 2023 IEEE Symposium on Security and Privacy (SP). IEEE, 2023.