Record summary
A quick snapshot of what this page covers.
Techniques2Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain7. AI System Safety, Failures, & LimitationsThe broad risk area this belongs to.
Risk profile
How this risk is described and categorized.
In many applications of AI-based systems such as medical healthcare and military services, the lack of verification of code may not be tolerable... due to some characteristics such as the non-linear and complex structure of AI-based solutions, existing solutions have been generally considered “black boxes”, not providing any information about what exactly makes them appear in their predictions and decision-making processes.
Domain7. AI System Safety, Failures, & Limitations
Subdomain7.4 > Lack of transparency or interpretability
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryVerifiability
Subcategoryn/a
Suggested mitigations
Defenses that may help with related attacks.
No propagated mitigations. No defense is available through the connected attack methods.
Source
Research source for this risk, when available.
Included resource
A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.