Mingshi Xu — accepted AI-conference papers

2023

Multi-step Jailbreaking Privacy Attacks on ChatGPT

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng +1

EMNLP 2023long findings

With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from LLMs, it is still challenging to steer AI-generated content (AI…

Cited by 0 Source ↗code ↗Scholar ↗

2023

Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence

Haoran Li, Mingshi Xu, Yangqiu Song

ACL 2023findings

Sentence-level representations are beneficial for various natural language processing tasks. It is commonly believed that vector representations can capture rich linguistic properties. Currently, large language models (LMs) achieve state-of-the-art performance on sentence embedding. However, some re…

Cited by 54 Source ↗PDF ↗code ↗Scholar ↗