厦门大学平台管理系统刘天天--中文主页-- Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization

刘天天

访问量：

开通时间：..

最后更新时间：..

当前位置：中文主页 >> 科学研究 >> 论文成果

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization

点击次数：

发表刊物：AAAI Conference on Artificial Intelligence(AAAI), 2026

是否译文：否

上一条：MicGuard: A Comprehensive Detection System against Out-of-band Injection Attacks for Different Level Microphone-based Devices.