Similar Items: When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI
- Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning
- Tracking Conversations: Measuring Content and Identity Exposure on AI Chatbots
- Data anonymization in the presence of outliers via invariant coordinate selection
- ActiveFlowMark: Assessing Tor Anonymity under Active Bandwidth Watermarking
- Democratizing Measurement of Critical Mobile Infrastructure: Security and Privacy in an Increasingly Centralized Communication Ecosystem
- LeakDojo: Decoding the Leakage Threats of RAG Systems