SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations

Summary

SNAPRAG is a black-box attack that extracts private knowledge bases from RAG systems using discrete token-mutation adversarial queries, without relying on external LLMs. The authors report that extracting half of the target knowledge base needs up to 6.77 times fewer queries than existing approaches, and within a fixed query budget it recovers up to 96.9% of the data. Against active defenses, it remained the leading attack on four of five targets, reaching a 50.7-96.3% extraction rate.

Topics

• Adversarial machine learning
• Retrieval-augmented generation

Related items

• MediumCVE-2026-125386: langchain4j-aideepin insecure direct object reference in message endpointsSimilar attack · NVD/CVE Database
• LowMGE: A Membership Guided Data Extraction Attack against Diffusion ModelsSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoGem5-Shark: Smaug-based Heterogeneous Deep Learning Accelerator Security and Robustness Evaluation and Characterization FrameworkSimilar attack · OpenAlex (peer-reviewed AI security)
• MediumCVE-2026-88982: Kubeflow Pipelines execution cache exposes cached outputs across namespacesSimilar attack · NVD/CVE Database
• MediumChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data ExfiltrationSimilar attack · Check Point Research