Acknowledgement
본 연구는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(NRF-2022R1F1A1076100). 또한 이 논문은 2024년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(No.2021-0-00724, 임베디드 시스템 악성코드 탐지·복원을 위한 RISC-V 기반 보안 CPU 아키텍처 핵심 기술 개발)
References
- OREKONDY, Tribhuvanesh; SCHIELE, Bernt; FRITZ, Mario. Knockoff nets: Stealing functionality of black-box models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019. p. 4954-4963.
- TRUONG, Jean-Baptiste, et al. Data-free model extraction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021. p. 4771-4780.
- PAL, Soham, et al. Activethief: Model extraction using active learning and unannotated public data. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020. p. 865-872.
- BARBALAU, Antonio, et al. Black-box ripper: Copying black-box models using generative evolutionary algorithms. Advances in Neural Information Processing Systems, 2020, 33:20120-20129.
- KARMAKAR, Pratik; BASU, Debabrota. Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack. Advances in Neural Information Processing Systems, 2024, 36.
- CHEN, Yanjiao, et al. D-dae: Defense-penetrating model extraction attacks. In: 2023 IEEE Symposium on Security and Privacy(SP). IEEE, 2023. p. 382-399.
- LV, Peizhuo, et al. MEA-Defender: A Robust Watermark against Model Extraction Attack. arXiv preprint arXiv:2401.15239, 2024.