A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
cs.CR, cs.CL
Submitted: 2026-06-17
Updated: 2026-08-26
Terminology
Sources
- Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B
- Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
- Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Mistral 7B
- Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
- Ignore Previous Prompt: Attack Techniques For Language Models
- Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Effective Prompt Extraction from Language Models
- Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples
- Formalizing and Benchmarking Prompt Injection Attacks and Defenses
- Constitutional AI: Harmlessness from AI Feedback
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
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