An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios

• URL: http://arxiv.org/abs/2606.29602v1
• Date: Sun, 28 Jun 2026 20:56:57 GMT
• Title: An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios
• Abstract summary: Large Language Models (LLMs) have rapidly evolved, transforming industries by automating complex tasks and generating human-like content.<n>As their adoption accelerates, prompt injection vulnerabilities have become increasingly apparent.<n>This paper presents an empirical evaluation of six state-of-the-art LLMs under diverse adversarial prompt scenarios.
• Score: 0.3499870393443268
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) have rapidly evolved, transforming industries by automating complex tasks and generating human-like content. However, as their adoption accelerates, prompt injection vulnerabilities have become increasingly apparent. Malicious actors exploit these weaknesses to generate phishing emails, deceptive websites, nd malware, posing serious security risks. This paper presents an empirical evaluation of six state-of-the-art LLMs (DeepSeek, GPT, Gemini, Grok, Llama, and Qwen) under diverse adversarial prompt scenarios, including direct and multi-stage obfuscated attacks across multiple languages and character encodings. The proposed framework measures how effectively current LLMs resist manipulation into performing harmful actions. Our findings reveal systematic vulnerabilities across all tested models. Even direct prompt injections frequently induce the generation of phishing content, websites, and malware, while elaborate prompts achieve even higher malicious compliance rates, particularly for phishing. Models such as DeepSeek, Gemini, and Grok show especially high susceptibility under complex instructions. Notably, non-English languages consistently exhibit higher compliance rates than English, exposing significant gaps in multilingual safety alignment. Although simple character encodings reduce malicious outputs, they do not eliminate them. These results highlight persistent challenges in LLM safety and underscore the urgent need for stronger defenses and improved security mechanisms to support the ethical and secure deployment of LLMs in cybersecurity sensitive contexts.

Related papers

• When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications [4.213098466542674]
  Large language models (LLMs) enable users to query data using conversational input rather than formal query languages such assql.<n>Malicious users can exploit these mechanisms by crafting adversarial prompts that manipulate model behavior and generate unsafe queries.<n>We propose a multi-layered security framework designed to detect and mitigate LLM-mediatedsql injection attacks.
  arXiv  Detail & Related papers  (2026-05-11T08:28:45Z)
• The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multi-Step Malware [6.5249834967502744]
  Large language model (LLM)-based systems have created a new attack surface that existing security frameworks inadequately address.<n>We propose that attacks targeting LLM-based applications constitute a distinct class of malware, which we term textitpromptware, and introduce a five-step kill chain model for analyzing these threats.
  arXiv  Detail & Related papers  (2026-01-14T16:57:04Z)
• Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models [0.0]
  camouflaged jailbreaking embeds malicious intent within seemingly benign language to evade existing safety mechanisms.<n>This paper investigates the construction and impact of camouflaged jailbreak prompts, emphasizing their deceptive characteristics and the limitations of traditional keyword-based detection methods.
  arXiv  Detail & Related papers  (2025-09-05T19:57:38Z)
• SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism [123.54980913741828]
  Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning.<n>MLLMs are susceptible to multimodal jailbreak attacks and hindering their safe deployment.<n>We propose Safe Prune-then-Restore (SafePTR), a training-free defense framework that selectively prunes harmful tokens at vulnerable layers while restoring benign features at subsequent layers.
  arXiv  Detail & Related papers  (2025-07-02T09:22:03Z)
• Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models [83.80177564873094]
  We propose a unified multimodal universal jailbreak attack framework.<n>We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP.<n>This study underscores the urgent need for robust safety measures in MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T04:33:56Z)
• Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context [45.821481786228226]
  We show that situation-driven adversarial full-prompts that leverage situational context are effective but much harder to detect.<n>We developed attacks that use movie scripts as situational contextual frameworks.<n>We enhanced the AdvPrompter framework with p-nucleus sampling to generate diverse human-readable adversarial texts.
  arXiv  Detail & Related papers  (2024-12-20T21:43:52Z)
• Endless Jailbreaks with Bijection Learning [3.5963161678592828]
  We introduce a powerful attack algorithm which fuzzes LLMs for safety vulnerabilities using randomly-generated encodings.<n>Our attack is extremely effective on a wide range of frontier language models.
  arXiv  Detail & Related papers  (2024-10-02T07:40:56Z)
• Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection [5.78117257526028]
  Large language models (LLMs) are renowned for their exceptional capabilities, and applying to a wide range of applications. This work focuses the impact of malicious prompt injection attacks which is one of most dangerous vulnerability on real LLMs applications. It examines to apply various BERT (Bidirectional Representations from Transformers) like multilingual BERT, DistilBert for classifying malicious prompts from legitimate prompts.
  arXiv  Detail & Related papers  (2024-09-20T08:48:51Z)
• CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion [117.178835165855]
  This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs. Our studies reveal a new and universal safety vulnerability of these models against code input. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization.
  arXiv  Detail & Related papers  (2024-03-12T17:55:38Z)
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
  We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities.<n>Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content.<n>We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
  arXiv  Detail & Related papers  (2023-12-21T01:08:39Z)
• Multilingual Jailbreak Challenges in Large Language Models [96.74878032417054]
  In this study, we reveal the presence of multilingual jailbreak challenges within large language models (LLMs) We consider two potential risky scenarios: unintentional and intentional. We propose a novel textscSelf-Defense framework that automatically generates multilingual training data for safety fine-tuning.
  arXiv  Detail & Related papers  (2023-10-10T09:44:06Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.