activity
20192026
most citedSecure Social Recommendation based on Secret Sharing

14 citations · 36 across the 5 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

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…