Master's Thesis in Data&AI: Privacy preserving RAG, Veenendaal

Overview Privacy is a critical challenge in deploying Retrieval-Augmented Generation (RAG) systems in sensitive domains. This thesis investigates how privacy-preserving techniques, such as differential privacy and synthetic data, can be integrated into RAG pipelines without degrading output quality. The research involves analyzing trade-offs, enhancing a promising method, and validating the approach with a proof of concept focused on real-world utility and privacy guarantees.

Areas of Interest

Information retrieval

AI

data privacy

NLP

differential privacy

Assignment Your research will include two components:

Literature Study

Review state-of-the-art methods for privacy-preserving RAG. Focus areas include:

Differentially Private In-Context Learning (e.g., DP-ICL2)

Synthetic document generation (e.g., SAGE)

Private fine-tuning (e.g., DP-SGD, masking techniques)

Analyze trade-offs between privacy guarantees and model utility.

Proof of Concept (PoC)

Select one promising technique and enhance it.

Ensure your improvement addresses gaps identified in the literature.

Build and evaluate a PoC integrating your privacy method into a RAG pipeline.

Evaluation metrics:

Privacy: Differential Privacy parameters (ε, δ)

Utility: Accuracy, BLEU/ROUGE scores, latency

Research Question How can privacy be preserved in Retrieval-Augmented Generation systems without sacrificing model utility?

Materials

Baseline project: RAG with Differential Privacy article: Privacy-Preserving In-context Learning with Differentially Private Few-shot Generation Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data language proficiency in Dutch is required.

Knowledge of privacy-preserving methods in machine learning and proficiency in working with RAG pipelines is preferred.

#J-18808-Ljbffr