# Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures

arXiv: https://arxiv.org/abs/2410.23308 · HTML: https://mlsanity.com/paper/2410.23308/

## Key facts

- Cited by 12 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.
- First posted on arXiv 28 Oct 2024.

## Placed in

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

## Built on by (most cited first, 12 of 12)

- [When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy](https://mlsanity.com/paper/2505.22888/) (2025)
- [SoK: Trust-Authorization Mismatch in LLM Agent Interactions](https://mlsanity.com/paper/2512.06914/) (2025)
- [Crosslingual On-Policy Self-Distillation for Multilingual Reasoning](https://mlsanity.com/paper/2605.09548/) (2026)
- [Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners](https://mlsanity.com/paper/2601.02996/) (2026)
- [A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages](https://mlsanity.com/paper/2510.09555/) (2025)
- [Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs](https://mlsanity.com/paper/2509.05883/) (2025)
- [Please Don't Kill My Vibe: Empowering Agents with Data Flow Control](https://mlsanity.com/paper/2512.05374/) (2025)
- [Architecture Matters for Multi-Agent Security](https://mlsanity.com/paper/2604.23459/) (2026)
- [Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense](https://mlsanity.com/paper/2510.16259/) (2025)
- [Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs](https://mlsanity.com/paper/2601.12359/) (2026)
- [VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models](https://mlsanity.com/paper/2507.00052/) (2025)
- [LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems](https://mlsanity.com/paper/2509.10682/) (2025)

## Abstract (arXiv)

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection tests, we observed a strong correlation between model parameters and vulnerability, with statistical analyses, such as logistic regression and random forest feature analysis, indicating that parameter size and architecture significantly influence susceptibility. Results revealed that 56 percent of tests led to successful prompt injections, emphasizing widespread vulnerability across various parameter sizes, with clustering analysis identifying distinct vulnerability profiles associated with specific model configurations. Additionally, our analysis uncovered correlations between certain prompt injection techniques, suggesting potential overlaps in vulnerabilities. These findings underscore the urgent need for robust, multi-layered defenses in LLMs deployed across critical infrastructure and sensitive industries. Successful prompt injection attacks could result in severe consequences, including data breaches, unauthorized access, or misinformation. Future research should explore multilingual and multi-step defenses alongside adaptive mitigation strategies to strengthen LLM security in diverse, real-world environments.