Privacy in AI Comparison Hub
3 papers - avg viability 4.0
Top Papers
- Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?(6.0)
A privacy-focused tool using VLMs to manage geolocation disclosure by respecting contextual integrity.
- CLIOPATRA: Extracting Private Information from LLM Insights(4.0)
CLIOPATRA exposes vulnerabilities in privacy-preserving LLM systems, revealing the inadequacy of current protections.
- Decoupling Generalizability and Membership Privacy Risks in Neural Networks(2.0)
Innovative training principle to decouple generalizability and privacy risks in neural networks.