Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents
cs.AI, cs.CL, cs.CR, cs.CY
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/joke2k/faker
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
- AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
- SPILLage: Agentic Oversharing on the Web
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- gpt-oss-120b & gpt-oss-20b Model Card
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents