Protecting User Prompts Via Character-Level Differential Privacy
Protecting User Prompts Via Character-Level Differential Privacy explores A novel differential privacy method to sanitize LLM prompts by perturbing characters, protecting sensitive information without explicit PII identification.. Commercial viability score: 7/10 in LLM Security.
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 $11K - $15K 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 ThisDifferentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft PromptViability: 5.0
- Builds On ThisDifferential Privacy in Generative AI Agents: Analysis and Optimal TradeoffsViability: 5.0
- Builds On ThisHuman-Centred LLM Privacy Audits: Findings and FrictionsViability: 3.0
- Builds On ThisBeyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive InformationViability: 2.0
- Builds On ThisWhat Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal Data