# Prompt injections as a tool for preserving identity in GAI image descriptions

arXiv: https://arxiv.org/abs/2510.16128 · HTML: https://mlsanity.com/paper/2510.16128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## 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, 10 of 10)

- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [Anti-DreamBooth: Protecting users from personalized text-to-image synthesis](https://mlsanity.com/paper/2303.15433/) (2023)
- [A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems](https://mlsanity.com/paper/2402.18649/) (2024)
- [Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models](https://mlsanity.com/paper/2310.13828/) (2023)
- [Identifying and Improving Disability Bias in GPT-Based Resume Screening](https://mlsanity.com/paper/2402.01732/) (2024)
- [Black Feminist Musings on Algorithmic Oppression](https://mlsanity.com/paper/2101.09869/) (2021)
- [Tackling Algorithmic Disability Discrimination in the Hiring Process: An Ethical, Legal and Technical Analysis](https://mlsanity.com/paper/2206.06149/) (2022)
- [An Autoethnographic Case Study of Generative Artificial Intelligence's Utility for Accessibility](https://mlsanity.com/paper/2308.09924/) (2023)
- [Laissez-Faire Harms: Algorithmic Biases in Generative Language Models](https://mlsanity.com/paper/2404.07475/) (2024)

## Abstract (arXiv)

Generative AI risks such as bias and lack of representation impact people who do not interact directly with GAI systems, but whose content does: indirect users. Several approaches to mitigating harms to indirect users have been described, but most require top down or external intervention. An emerging strategy, prompt injections, provides an empowering alternative: indirect users can mitigate harm against them, from within their own content. Our approach proposes prompt injections not as a malicious attack vector, but as a tool for content/image owner resistance. In this poster, we demonstrate one case study of prompt injections for empowering an indirect user, by retaining an image owner's gender and disabled identity when an image is described by GAI.