Search Results - red+teaming

1 Results Sort By:
Exploiting Class Probabilities for Black-Box Sentence-Level Attacks
Background Text classification models have become increasingly prevalent in cybersecurity applications, but remain susceptible to adversarial examples (e.g., carefully crafted sentences with human-unrecognizable changes to the inputs, that are misclassified). Adversarial attacks provide profound insights into the classifiers’ vulnerabilities,...
Published: 8/21/2025   |   Inventor(s): Raha Moraffah, Huan Liu
Keywords(s): Machine Learning, Natural Language Processing, Red teaming, Security
Category(s): Physical Science, Applied Technologies, Artificial Intelligence/Machine Learning, Cybersecurity