Xinpeng Ti

2 accepted papers

2026

An Invariant Latent Space Perspective on Language Model Inversion

Wentao Ye, Jiaqi Hu, Haobo Wang, Xinpeng Ti, Zhiqing Xiao, Hao Chen +4

AAAI 2026technical

Language model inversion (LMI), i.e., recovering hidden prompts from outputs, emerges as a concrete threat to user privacy and system security. We recast LMI as reusing the LLM

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Towards Reverse Engineering of Language Models: A Survey

Xinpeng Ti, Wentao Ye, Zhifang Zhang, Junbo Zhao, Chang Yao, Lei Feng +1

EMNLP 2025

With the continuous development of language models and the widespread availability of various types of accessible interfaces, large language models (LLMs) have been applied to an increasing number of fields. However, due to the vast amounts of data and computational resources required for model deve

Cited by 0 Source ↗PDF ↗Scholar ↗