Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics
cs.CR, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Pr$\epsilon\epsilon$mpt: Sanitizing Sensitive Prompts for LLMs
- Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications
- BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
- Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data