# Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models

arXiv: https://arxiv.org/abs/2601.17911 · HTML: https://mlsanity.com/paper/2601.17911/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 1 of its 1 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 1 of 1)

- [PromptBench: A Unified Library for Evaluation of Large Language Models](https://mlsanity.com/paper/2312.07910/) (2023)

## Built on by (most cited first, 1 of 1)

- [False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift](https://mlsanity.com/paper/2610.01535/) (2026)

## Abstract (arXiv)

Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal as a local decision boundary and examining its stability under structured perturbations. We evaluated two models, GPT-4.1 and GPT-4o, using 3,274 perturbation runs derived from refusal-inducing prompt injection attempts. Each base prompt was subjected to 25 perturbations across five structured families, with outcomes manually coded as Refusal, Partial Compliance, or Full Compliance. Using chi-square tests, logistic regression, mixed-effects modeling, and a novel Refusal Boundary Entropy (RBE) metric, we demonstrate that while both models refuse >94% of attempts, refusal instability is persistent and non-uniform. Approximately one-third of initial refusal-inducing prompts exhibited at least one "refusal escape," a transition to compliance under perturbation. We find that artifact type is a stronger predictor of refusal failure than perturbation style. Textual artifacts, such as ransomware notes, exhibited significantly higher instability, with flip rates exceeding 20%. Conversely, executable malware artifacts showed zero refusal escapes in both models. While GPT-4o demonstrated tighter refusal enforcement and lower RBE than GPT-4.1, it did not eliminate artifact-dependent risks. These findings suggest that single-prompt evaluations systematically overestimate safety robustness. We conclude that refusal behavior is a probabilistic, artifact-dependent boundary phenomenon rather than a stable binary property, requiring a shift in how LLM safety is measured and audited.