# AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

arXiv: https://arxiv.org/abs/2602.13597 · HTML: https://mlsanity.com/paper/2602.13597/

## Key facts

- Cited by 5 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 26 of its 31 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## 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, 26 of 26)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game](https://mlsanity.com/paper/2311.01011/) (2023)
- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks](https://mlsanity.com/paper/2504.11358/) (2025)
- [PLeak: Prompt Leaking Attacks against Large Language Model Applications](https://mlsanity.com/paper/2405.06823/) (2024)
- [Dissecting Adversarial Robustness of Multimodal LM Agents](https://mlsanity.com/paper/2406.12814/) (2024)
- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- [Get my drift? Catching LLM Task Drift with Activation Deltas](https://mlsanity.com/paper/2406.00799/) (2024)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [Can Indirect Prompt Injection Attacks Be Detected and Removed?](https://mlsanity.com/paper/2502.16580/) (2025)
- [A Critical Evaluation of Defenses against Prompt Injection Attacks](https://mlsanity.com/paper/2505.18333/) (2025)
- [PromptLocate: Localizing Prompt Injection Attacks](https://mlsanity.com/paper/2510.12252/) (2025)
- [ASIDE: Architectural Separation of Instructions and Data in Language Models](https://mlsanity.com/paper/2503.10566/) (2025)

## Built on by (most cited first, 5 of 5)

- [When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift](https://mlsanity.com/paper/2602.14161/) (2026)
- [Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense](https://mlsanity.com/paper/2605.30837/) (2026)
- [Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models](https://mlsanity.com/paper/2606.07808/) (2026)
- [Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails](https://mlsanity.com/paper/2609.05535/) (2026)
- [Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents](https://mlsanity.com/paper/2610.03448/) (2026)

## Abstract (arXiv)

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typically classify any input with instruction as malicious, leading to misclassification of benign inputs containing instructions that align with the intended task. In this work, we account for the instruction hierarchy and distinguish among three categories: inputs with misaligned instructions, inputs with aligned instructions, and non-instruction inputs. We introduce AlignSentinel, a three-class classifier that leverages features derived from LLM's attention maps to categorize inputs accordingly. To support evaluation, we construct the first systematic benchmark containing inputs from all three categories. Experiments on both our benchmark and existing ones--where inputs with aligned instructions are largely absent--show that AlignSentinel accurately detects inputs with misaligned instructions and substantially outperforms baselines.