> For the complete documentation index, see [llms.txt](https://documentations.seclea.com/fda-ai-based-samd/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://documentations.seclea.com/fda-ai-based-samd/accuracy-robustness-and-cybersecurity-arc/arc04-cyber-security-assessment.md).

# ARC04 - Cyber Security Assessment

Resilience against attempts by unauthorised third parties to alter the use or performance of a High-Risk AI system

1. The technical solutions to ensure the cybersecurity of high-risk AI systems shall be appropriate to the relevant circumstances and the risks.
2. The technical solutions to address AI-specific vulnerabilities shall include, where appropriate, measures to prevent and control attacks trying to manipulate the training dataset (‘data poisoning’), inputs designed to cause the model to make a mistake (‘adversarial examples’), or model flaws.