8 citations · 8 across the 2 of their papers we have counts for
2 papers
cs.CR2026
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
Zhicong Huang, Cheng Hong, Tao Wei
Cloud-based language model services routinely process prompts containing sensitive information. Obfuscation-based defenses---including ObfusLM, SentinelLMs, TextObfuscator, and DPN…
cs.CR2023★ 8 cited
PUMA: Secure Inference of LLaMA-7B in Five Minutes
Ye Dong, Wen-jie Lu, Yancheng Zheng +7
With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts…