All terms
Adversarial Robustness
Resilience of an ML model to inputs deliberately crafted to cause misclassification.
Reviewed by Christian Espinosa, Founder, Blue Goat CyberLast reviewed May 5, 2026
Definition
Adversarial examples - small, often imperceptible perturbations - can flip medical-imaging predictions. Robustness evaluation, input sanitization, and detection of out-of-distribution inputs are emerging expectations for safety-critical AI.What this means in practice
Particularly relevant for AI radiology and pathology devices where image acquisition is partially under attacker influence.Primary references
3 sourcesLink health: 2 verified 1 needs review· last checked 2026-05-09
NIST·1FDA·1IMDRF·1
- 1
NIST AI 100-2Needs reviewNISTcsrc.nist.gov
- 2
FDA - AI/ML-Enabled Medical DevicesVerifiedFDAfda.gov
- 3
IMDRF - Software as a Medical DeviceVerifiedIMDRFimdrf.org
Inline markers like [1] jump to the matching reference above.