SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations
cs.CR
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- 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
- Retrieval-Augmented Generation for Large Language Models: A Survey
- The Llama 3 Herd of Models
- REALM: Retrieval-Augmented Language Model Pre-Training
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications
- Prompt Repetition Improves Non-Reasoning LLMs
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- Prompt Injection attack against LLM-integrated Applications
- Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models
- GPT-4 Technical Report
- Ignore Previous Prompt: Attack Techniques For Language Models
- Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
- Prompt Stealing Attacks Against Large Language Models
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Qwen2 Technical Report
- Effective Prompt Extraction from Language Models
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