Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs
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_ | 1866909339726381056 |
|---|---|
| author | Momcilovic, Tomas Bueno Buesser, Beat Zizzo, Giulio Purcell, Mark Balta, Dian |
| author_facet | Momcilovic, Tomas Bueno Buesser, Beat Zizzo, Giulio Purcell, Mark Balta, Dian |
| contents | Large language models are prone to misuse and vulnerable to security threats, raising significant safety and security concerns. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain contexts, but faces implementation challenges due to the lack of standards, complexity of LLMs and emerging security vulnerabilities. Our research introduces a framework using ontologies, assurance cases, and factsheets to support engineers and stakeholders in understanding and documenting AI system compliance and security regarding adversarial robustness. This approach aims to ensure that LLMs adhere to regulatory standards and are equipped to counter potential threats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05306 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs Momcilovic, Tomas Bueno Buesser, Beat Zizzo, Giulio Purcell, Mark Balta, Dian Cryptography and Security Artificial Intelligence Large language models are prone to misuse and vulnerable to security threats, raising significant safety and security concerns. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain contexts, but faces implementation challenges due to the lack of standards, complexity of LLMs and emerging security vulnerabilities. Our research introduces a framework using ontologies, assurance cases, and factsheets to support engineers and stakeholders in understanding and documenting AI system compliance and security regarding adversarial robustness. This approach aims to ensure that LLMs adhere to regulatory standards and are equipped to counter potential threats. |
| title | Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2410.05306 |