Ollama本地大模型爆严重漏洞CVE-2026-7482，堆越界读取可导致隐私泄露，隐私神话破灭
The Bleeding Llama vulnerability shows why running AI locally is not a security strategy Running an LLM locally feels like a privacy win. No cloud API…
新方法GELO专为共享加速器场景设计，有效保护开源大模型的提示词隐私，对抗内存读取攻击。
arXiv:2603.05035v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly served on shared accelerators where an adversa…
揭穿LLM数据隐私漏洞：通过训练数据投毒定向提取未见样本，AI安全新威胁。
arXiv:2606.17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private health…
研究发现大模型向AI代理泄露个人数据多于向人类，揭示“交谈者效应”及注意抑制机制
arXiv:2606.09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their i…
提出基于top-1预测差距的Gap-K%方法，精准检测LLM预训练数据，破解隐私与版权难题
arXiv:2601.19936v2 Announce Type: replace-cross Abstract: The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significan…