MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
cs.CR
Submitted: 2025-12-09
Updated: 2026-08-31
Code: https://github.com/SuburbiaXX/MIRAGE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time
- Detecting Language Model Attacks with Perplexity
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
- The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Retrieval-Augmented Generation for Large Language Models: A Survey
- GLTR: Statistical Detection and Visualization of Generated Text
- External Data Extraction Attacks against Retrieval-Augmented Large Language Models
- GPT-4o System Card
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- Mistral 7B
- Prompt Injection attack against LLM-integrated Applications
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- gpt-oss-120b & gpt-oss-20b Model Card
- Ignore Previous Prompt: Attack Techniques For Language Models
- Qwen3 Technical Report
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs