공대생 도전 일지

https://aclanthology.org/2025.naacl-long.614/ EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMsSam Lin, Wenyue Hua, Zhenting Wang, Mingyu Jin, Lizhou Fan, Yongfeng Zhang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)..

https://arxiv.org/abs/2410.09457 Power-Softmax: Towards Secure LLM Inference over Encrypted DataModern cryptographic methods for implementing privacy-preserving LLMs such as Homomorphic Encryption (HE) require the LLMs to have a polynomial form. Forming such a representation is challenging because Transformers include non-polynomial components, sucharxiv.orgHE 기반의 LLM Inference는 Polynomial이어야 함!..