CWE-1039 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.

• Availability, Integrity: Bypass Protection Mechanism, DoS: Resource Consumption (Other), DoS: Instability — When the automated mechanism is used in a protection mechanism to automatically classify input streams, and those classifications are used for security-critical decisions, then any mistake in classification can introduce a vulnerability that allows attackers to cause the product to make the wrong security decision or disrupt service of the automated mechanism. An attacker may be able to craft inputs that are misinterpreted in a way that grants excess privileges. • Confidentiality: Read Application Data — This weakness could lead to breaches of data privacy through exposing features of the training data, e.g., by using membership inference attacks or prompt injection attacks. • Other: Varies by Context — The consequences depend on how the application applies or integrates the affected algorithm.

• [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. • [Integration] Reactive defenses such as input sanitization, defensive distillation, and input transformations can all be implemented before input data reaches the algorithm for inference. • [Integration] Consider reducing the output granularity of the inference/prediction such that attackers cannot gain additional information due to leakage in order to craft adversarially perturbed data.

• Dynamic Analysis with Manual Results Interpretation: Use indicators from model performance deviations such as sudden drops in accuracy or unexpected outputs to verify the model. • Dynamic Analysis with Manual Results Interpretation: Use indicators from input data collection mechanisms to verify that inputs are statistically within the distribution of the training and test data. • Architecture or Design Review: Use multiple models or model ensembling techniques to check for consistency of predictions/inferences.

• CVE-2025-26644: biometric authentication capability allows attackers to spoof biometric data and bypass authentication using adversarial input perturbations that cause the ML model to accepting the input