Unlearning Sensitive Data in Reasoning Models: A Privacy-First Approac
STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models explores "STaR provides a robust framework for privacy-preserving unlearning in large reasoning models, protecting sensitive data at all reasoning levels.". Commercial viability score: 7/10 in AI Privacy.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisESTAR: Early-Stopping Token-Aware Reasoning For Efficient InferenceViability: 6.0
- Builds On ThisSecure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based AgentsViability: 6.0
- Builds On ThisStop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMsViability: 6.0
- Builds On ThisLearning Structured Reasoning via Tractable Trajectory ControlViability: 5.0
- Builds On ThisStable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation