Acknowledgement
이 논문은 2025년도 BK21 FOUR 정보기술 미래인재 교육연구단에 의하여 지원되었음. 이 논문은 2025년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(RS-2023-00277326). 이 논문은 2025년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (No.2021-0-00528, 하드웨어 중심 신뢰계산기반과 분산 데이터보호박스를 위한 표준 프로토콜 개발). 이 논문은 2025년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(IITP-2023-RS-2023-00256081). 본 연구는 과학기술정보통신부 및 정보통신기획평가원의 대학ICT연구센터육성지원사업의 연구결과로 수행되었음(IITP-2023-2020-0-01602).
References
- Ebel, Austin, Karthik Garimella, and Brandon Reagen. "Orion: A Fully Homomorphic Encryption Framework for Deep Learning." Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. 2025.
- Wang, Yongqin, Rachit Rajat, and Murali Annavaram. "Mpc-pipe: An efficient pipeline scheme for semi-honest mpc machine learning." Proceedings of the 29th ACM International Conference on Architectural Support forProgramming Languages and Operating Systems, Volume 4. 2024.
- Tramèr, Florian, et al. "Stealing machinelearning models via prediction {APIs}." 25thUSENIX security symposium (USENIXSecurity16). 2016.
- Shokri, Reza, et al. "Membership inferenceattacks against machine learning models." 2017IEEE symposium on security and privacy (SP). IEEE, 2017.
- Hanzlik, Lucjan, et al. "Mlcapsule: Guardedoffline deployment of machine learning as aservice." Proceedings of the IEEE/CVFconferenceon computer vision and pattern recognition. 2021.
- Mo, Fan, et al. "Darknetz: towards modelprivacy at the edge using trusted executionenvironments." Proceedings of the 18thInternational Conference on Mobile Systems, Applications, and Services. 2020.
- Shen, Tianxiang, et al. "{SOTER}: Guardingblack-box inference for general neural networksat the edge." 2022 USENIX Annual TechnicalConference (USENIX ATC 22). 2022.
- Xiang, Yecheng, et al. "Aegisdnn: Dependableand timely execution of dnn tasks with sgx." 2021IEEE Real-Time Systems Symposium (RTSS). IEEE, 2021.
- Zhang, Ziqi, et al. "No privacy left outside: Onthe (in-) security of tee-shielded dnn partition foron-device ml." 2024 IEEE Symposium on Securityand Privacy (SP). IEEE, 2024.
- Sun, Zhichuang, et al. "Shadownet: A secureand efficient on-device model inference system forconvolutional neural networks." 2023 IEEESymposium on Security and Privacy (SP). IEEE, 2023.
- Zhang, Zheng, et al. "GroupCover: A Secure, Efficient and Scalable Inference Framework forOn-device Model Protection based on TEEs."Forty-first International Conference on MachineLearning. 2024.