Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs

Authors: Tomas Bueno Momcilovic, Beat Buesser, Giulio Zizzo, Mark Purcell, Dian Balta
Published: 2024-10-04

Source: https://arxiv.org/abs/2410.05306

PDF: https://arxiv.org/pdf/2410.05306

AIにより推定されたラベル

AIコンプライアンス LLMセキュリティ フレームワーク

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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.