New CAREATTACK framework exploits RAG systems via malicious knowledge injection

Researchers have developed CAREATTACK, a novel framework for injecting malicious knowledge into retrieval-augmented generation (RAG) systems. This model-centric attack targets the dense retrieval model's parameters, promoting harmful information over benign evidence. CAREATTACK includes stages for conflict-aware editing and anchor repair to ensure attack effectiveness while minimizing impact on non-target prompts. Demonstrated on Qwen3-Embedding-0.6B and BGE-M3, the method successfully manipulates RAG systems, highlighting a significant security vulnerability in applications built on open-source retrieval models. AI

IMPACT This research reveals a practical attack surface in RAG systems, potentially impacting the security and reliability of AI applications.

RANK_REASON The cluster describes a new academic paper detailing a novel attack framework on LLM-based RAG systems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• CAREATTACK
• Qwen3-Embedding-0.6B

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →