Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909448311668736 |
|---|---|
| author | Khowaja, Sunder Ali Khuwaja, Parus Dev, Kapal Hamadi, Hussam Al Zeydan, Engin |
| author_facet | Khowaja, Sunder Ali Khuwaja, Parus Dev, Kapal Hamadi, Hussam Al Zeydan, Engin |
| contents | Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that ZSM networks will be able to support LLMs as a service, as they provide ultra reliable low-latency communications and closed loop massive connectivity. However, LLMs are vulnerable to data and model privacy issues that affect the trustworthiness of LLMs to be deployed for user-based services. In this paper, we explore the security vulnerabilities associated with fine-tuning LLMs in ZSM networks, in particular the membership inference attack. We define the characteristics of an attack network that can perform a membership inference attack if the attacker has access to the fine-tuned model for the downstream task. We show that the membership inference attacks are effective for any downstream task, which can lead to a personal data breach when using LLM as a service. The experimental results show that the attack success rate of maximum 92% can be achieved on named entity recognition task. Based on the experimental analysis, we discuss possible defense mechanisms and present possible research directions to make the LLMs more trustworthy in the context of ZSM networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00722 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities Khowaja, Sunder Ali Khuwaja, Parus Dev, Kapal Hamadi, Hussam Al Zeydan, Engin Cryptography and Security Artificial Intelligence Distributed, Parallel, and Cluster Computing Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that ZSM networks will be able to support LLMs as a service, as they provide ultra reliable low-latency communications and closed loop massive connectivity. However, LLMs are vulnerable to data and model privacy issues that affect the trustworthiness of LLMs to be deployed for user-based services. In this paper, we explore the security vulnerabilities associated with fine-tuning LLMs in ZSM networks, in particular the membership inference attack. We define the characteristics of an attack network that can perform a membership inference attack if the attacker has access to the fine-tuned model for the downstream task. We show that the membership inference attacks are effective for any downstream task, which can lead to a personal data breach when using LLM as a service. The experimental results show that the attack success rate of maximum 92% can be achieved on named entity recognition task. Based on the experimental analysis, we discuss possible defense mechanisms and present possible research directions to make the LLMs more trustworthy in the context of ZSM networks. |
| title | Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities |
| topic | Cryptography and Security Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2408.00722 |