LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908537612926976 |
|---|---|
| author | Moia, Vitor Hugo Galhardo Sanz, Igor Jochem Rebello, Gabriel Antonio Fontes de Meneses, Rodrigo Duarte Hitaj, Briland Lindqvist, Ulf |
| author_facet | Moia, Vitor Hugo Galhardo Sanz, Igor Jochem Rebello, Gabriel Antonio Fontes de Meneses, Rodrigo Duarte Hitaj, Briland Lindqvist, Ulf |
| contents | The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing security to LLM-based systems is a great challenge, as both traditional threats to software applications and threats targeting LLMs and their integration must be mitigated. In this survey, we shed light on security and privacy concerns of such LLM-based systems by performing a systematic review and comprehensive categorization of threats and defensive strategies considering the entire software and LLM life cycles. We analyze real-world scenarios with distinct characteristics of LLM usage, spanning from development to operation. In addition, threats are classified according to their severity level and to which scenarios they pertain, facilitating the identification of the most relevant threats. Recommended defense strategies are systematically categorized and mapped to the corresponding life cycle phase and possible attack strategies they attenuate. This work paves the way for consumers and vendors to understand and efficiently mitigate risks during integration of LLMs in their respective solutions or organizations. It also enables the research community to benefit from the discussion of open challenges and edge cases that may hinder the secure and privacy-preserving adoption of LLM-based systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems Moia, Vitor Hugo Galhardo Sanz, Igor Jochem Rebello, Gabriel Antonio Fontes de Meneses, Rodrigo Duarte Hitaj, Briland Lindqvist, Ulf Cryptography and Security Artificial Intelligence Computation and Language Emerging Technologies Machine Learning The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing security to LLM-based systems is a great challenge, as both traditional threats to software applications and threats targeting LLMs and their integration must be mitigated. In this survey, we shed light on security and privacy concerns of such LLM-based systems by performing a systematic review and comprehensive categorization of threats and defensive strategies considering the entire software and LLM life cycles. We analyze real-world scenarios with distinct characteristics of LLM usage, spanning from development to operation. In addition, threats are classified according to their severity level and to which scenarios they pertain, facilitating the identification of the most relevant threats. Recommended defense strategies are systematically categorized and mapped to the corresponding life cycle phase and possible attack strategies they attenuate. This work paves the way for consumers and vendors to understand and efficiently mitigate risks during integration of LLMs in their respective solutions or organizations. It also enables the research community to benefit from the discussion of open challenges and edge cases that may hinder the secure and privacy-preserving adoption of LLM-based systems. |
| title | LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2509.10682 |