Inadequate Detection or Handling of Adversarial Input Perturbations in Automated Recognition Mechanism

The product uses an automated mechanism such as machine learning to recognize complex data inputs (e.g. image or audio) as a particular concept or category, but it does not properly detect or handle inputs that have been modified or constructed in a way that causes the mechanism to detect a different, incorrect concept.

We track 1 vulnerability of this type. 100% are rated high or critical, and the average CVSS score is 9.3.

How this weakness is prevented

• Architecture and Design: Algorithmic modifications such as model pruning or compression can help mitigate this weakness. Model pruning ensures that only weights that are most relevant to the task are used in the inference of incoming data and has shown resilience to adversarial perturbed data.
• Architecture and Design: Consider implementing adversarial training, a method that introduces adversarial examples into the training data to promote robustness of algorithm at inference time.
• Architecture and Design: Consider implementing model hardening to fortify the internal structure of the algorithm, including techniques such as regularization and optimization to desensitize algorithms to minor input perturbations and/or changes.
• Implementation: Consider implementing multiple models or using model ensembling techniques to improve robustness of individual model weaknesses against adversarial input perturbations.
• Implementation: Incorporate uncertainty estimations into the algorithm that trigger human intervention or secondary/fallback software when reached. This could be when inference predictions and confidence scores are abnormally high/low comparative to expected model performance.