DefensesarXiv 2610.01184
ReCast：在固定媒体接口下保护多模态推理的隐私框架
提出 RECAST，本地改写图表与语音并做可逆数值映射以保护远程推理隐私
- arXiv
- 2610.01184
- Published
- Layer
- Application layer
- Setting
- LLM applications
- ComponentVision
All papers
Filter2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Another 265papers do not have category tags yet and are not included in filtered results.
- DefensesarXiv 2609.21363
用扩散模型隐空间扰动防御视觉语言模型的地理位置隐私泄露
提出扩散潜空间地理扰动防御，抑制视觉语言模型泄露精确地理位置
- arXiv
- 2609.21363
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Attacker
- Black-box
- Evaluated models
- GPT-4.1, GPT-5, Gemini 2.5 Pro and others5
- AttacksMalicious use
- ComponentVision
- DefensesarXiv 2609.15671
QPriv-VL：面向视觉语言模型的问题引导 token 裁剪隐私防御
提出 QPriv-VL，用问题引导剪枝降低分布式视觉问答的隐私泄露
- arXiv
- 2609.15671
- Published
- Setting
- Models and APIs
- Evaluated models
- LLaVA-1.5-7B, Llama-2
- AttacksExtraction and theft
- ComponentVision
AbstractQPriv-VL 在切层前按问题相关度与 DINOv2 敏感度剪视觉 token，作者称能在约四成 token 下兼顾准确率与四类攻击。
QPriv-VL 把问题引导的视觉 token 剪枝做成分布式 VQA 的客户端隐私防御，而不是只做集中式推理加速。
You have reached the end