ARC04 - Cyber Security Assessment
Resilience against attempts by unauthorised third parties to alter the use or performance of an AI application.
Upload a document detailing your assessment of the measures in place to make sure that the AI system is resilient as regards attempts by unauthorised third parties to change its use or performance by exploiting the system vulnerabilities and whether they are appropriate to the relevant circumstances and the risks. List any known or foreseeable circumstances that may have an impact on that.
Upload a document detailing your assessment of the measures in place to address AI-specific vulnerabilities. This will 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. List any known or foreseeable circumstances that may have an impact on that.
Last updated