Malla: Demystifying Real-world Large Language Model Integrated Malicious Services
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910570681204736 |
|---|---|
| author | Lin, Zilong Cui, Jian Liao, Xiaojing Wang, XiaoFeng |
| author_facet | Lin, Zilong Cui, Jian Liao, Xiaojing Wang, XiaoFeng |
| contents | The underground exploitation of large language models (LLMs) for malicious services (i.e., Malla) is witnessing an uptick, amplifying the cyber threat landscape and posing questions about the trustworthiness of LLM technologies. However, there has been little effort to understand this new cybercrime, in terms of its magnitude, impact, and techniques. In this paper, we conduct the first systematic study on 212 real-world Mallas, uncovering their proliferation in underground marketplaces and exposing their operational modalities. Our study discloses the Malla ecosystem, revealing its significant growth and impact on today's public LLM services. Through examining 212 Mallas, we uncovered eight backend LLMs used by Mallas, along with 182 prompts that circumvent the protective measures of public LLM APIs. We further demystify the tactics employed by Mallas, including the abuse of uncensored LLMs and the exploitation of public LLM APIs through jailbreak prompts. Our findings enable a better understanding of the real-world exploitation of LLMs by cybercriminals, offering insights into strategies to counteract this cybercrime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03315 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Malla: Demystifying Real-world Large Language Model Integrated Malicious Services Lin, Zilong Cui, Jian Liao, Xiaojing Wang, XiaoFeng Cryptography and Security Artificial Intelligence The underground exploitation of large language models (LLMs) for malicious services (i.e., Malla) is witnessing an uptick, amplifying the cyber threat landscape and posing questions about the trustworthiness of LLM technologies. However, there has been little effort to understand this new cybercrime, in terms of its magnitude, impact, and techniques. In this paper, we conduct the first systematic study on 212 real-world Mallas, uncovering their proliferation in underground marketplaces and exposing their operational modalities. Our study discloses the Malla ecosystem, revealing its significant growth and impact on today's public LLM services. Through examining 212 Mallas, we uncovered eight backend LLMs used by Mallas, along with 182 prompts that circumvent the protective measures of public LLM APIs. We further demystify the tactics employed by Mallas, including the abuse of uncensored LLMs and the exploitation of public LLM APIs through jailbreak prompts. Our findings enable a better understanding of the real-world exploitation of LLMs by cybercriminals, offering insights into strategies to counteract this cybercrime. |
| title | Malla: Demystifying Real-world Large Language Model Integrated Malicious Services |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2401.03315 |