# Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

arXiv: https://arxiv.org/abs/2410.09102 · HTML: https://mlsanity.com/paper/2410.09102/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 40 of its 54 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)
- [AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs](https://mlsanity.com/paper/2404.07921/) (2024)
- [Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game](https://mlsanity.com/paper/2311.01011/) (2023)

## Built on by (most cited first, 30 of 67)

- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents](https://mlsanity.com/paper/2412.16682/) (2024)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [A Critical Evaluation of Defenses against Prompt Injection Attacks](https://mlsanity.com/paper/2505.18333/) (2025)
- [RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection](https://mlsanity.com/paper/2510.04885/) (2025)
- [Defending Against Prompt Injection with DataFilter](https://mlsanity.com/paper/2510.19207/) (2025)
- [Control Illusion: The Failure of Instruction Hierarchies in Large Language Models](https://mlsanity.com/paper/2502.15851/) (2025)
- [Defending Against Prompt Injection With a Few DefensiveTokens](https://mlsanity.com/paper/2507.07974/) (2025)
- [A Closer Look at System Prompt Robustness](https://mlsanity.com/paper/2502.12197/) (2025)
- [PromptLocate: Localizing Prompt Injection Attacks](https://mlsanity.com/paper/2510.12252/) (2025)
- [The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey](https://mlsanity.com/paper/2603.11088/) (2026)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [ASIDE: Architectural Separation of Instructions and Data in Language Models](https://mlsanity.com/paper/2503.10566/) (2025)
- [MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks](https://mlsanity.com/paper/2602.09222/) (2026)
- [PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features](https://mlsanity.com/paper/2510.14005/) (2025)
- [ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data](https://mlsanity.com/paper/2512.09321/) (2025)
- [VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit](https://mlsanity.com/paper/2601.05755/) (2026)
- [Prompt Injection as Role Confusion](https://mlsanity.com/paper/2603.12277/) (2026)
- [A Framework for Formalizing LLM Agent Security](https://mlsanity.com/paper/2603.19469/) (2026)
- [IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs](https://mlsanity.com/paper/2603.10521/) (2026)
- [Systems Security Foundations for Agentic Computing](https://mlsanity.com/paper/2512.01295/) (2025)
- [Defenses Against Prompt Attacks Learn Surface Heuristics](https://mlsanity.com/paper/2601.07185/) (2026)
- [The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck](https://mlsanity.com/paper/2605.11039/) (2026)
- [Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks](https://mlsanity.com/paper/2507.02735/) (2025)
- [Optimizing Agent Planning for Security and Autonomy](https://mlsanity.com/paper/2602.11416/) (2026)
- [Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations](https://mlsanity.com/paper/2505.18907/) (2025)
- [The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism](https://mlsanity.com/paper/2601.09625/) (2026)
- [Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals](https://mlsanity.com/paper/2603.03258/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabilities is the lack of an instruction hierarchy. Modern LLM architectures treat all inputs equally, failing to distinguish between and prioritize various types of instructions, such as system messages, user prompts, and data. As a result, lower-priority user prompts may override more critical system instructions, including safety protocols. Existing approaches to achieving instruction hierarchy, such as delimiters and instruction-based training, do not address this issue at the architectural level. We introduce the Instructional Segment Embedding (ISE) technique, inspired by BERT, to modern large language models, which embeds instruction priority information directly into the model. This approach enables models to explicitly differentiate and prioritize various instruction types, significantly improving safety against malicious prompts that attempt to override priority rules. Our experiments on the Structured Query and Instruction Hierarchy benchmarks demonstrate an average robust accuracy increase of up to 15.75% and 18.68%, respectively. Furthermore, we observe an improvement in instruction-following capability of up to 4.1% evaluated on AlpacaEval. Overall, our approach offers a promising direction for enhancing the safety and effectiveness of LLM architectures.