Adversarial Attack
An attack method targeting AI models that introduces imperceptible perturbations to input data, causing the model to produce incorrect predictions or outputs. Adversarial attacks have been extensively studied in domains such as image recognition and natural language processing.
Timeline (last 90 days)
Adversarial attacks involve applying imperceptibly small perturbations to input data that cause AI models to make erroneous judgments, and have been demonstrated to be feasible in both image recognition and text processing tasks.
Adversarial attacks targeting specific detectors can fool detection models by adding imperceptibly small perturbations to generated content.
All Facts (2)
Adversarial attacks involve applying imperceptibly small perturbations to input data that cause AI models to make erroneous judgments, and have been demonstrated to be feasible in both image recognition and text processing tasks.
50%UnverifiedAdversarial attacks targeting specific detectors can fool detection models by adding imperceptibly small perturbations to generated content.
50%