Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"GPAI developers often run evaluations ofual-use capabilities to decide whether it is safe to deploy. In some cases, these evaluations may fail to elicit these capabilities, either due to benign reasons or strategic action - by either the de- velopers, malicious actors, or arise unintentionally in the model during training [84, 97]. A GPAI model may strategically underperform or limit its performance during capability evaluations in order to be classified as safe for deployment. This underperformance could prevent the model from being identified as potentially dual use."
Suggested mitigations
Defenses that may help with related attacks.
Control Access to AI Models and Data at Rest
Sanitize Training Data
Verify AI Artifacts
Maintain AI Dataset Provenance
Source
Research source for this risk, when available.
Included resource
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.