DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

arXiv:2507.15042 · cs.AI, cs.IR · Submitted 2025-07-20 · Read on arXiv

cs.AI, cs.IR

Submitted: 2025-07-20

Updated: 2025-07-20

Terminology

• RAG — 3× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation — 2× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Differential Evolution — 1× in this paper
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 21 episodes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems