An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference

An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference Yu Lin author Qizhi Zhang author Quanwei Cai author Jue Hong author Wu Ye author Huiqi Liu author Bing Duan author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication lin-etal-2024-inversion 10.18653/v1/2024.emnlp-main.126 https://aclanthology.org/2024.emnlp-main.126/ 2024-11 2100 2104