Search Results - raha+moraffah

3 Results Sort By:
Exploiting Vulnerabilities and Security Threats in Retrieval-Augmented Generative Models: The LIAR Attack Framework
Invention Description Retrieval-Augmented Generative (RAG) models boost generative AI’s accuracy by connecting large language models (LLMs) with the most current, external, knowledge sources. RAG models are widely used in fact-checking, information retrieval, and AI-driven search engines. Despite their utility, adversarial threats can exploit...
Published: 1/30/2026   |   Inventor(s): Zhen Tan, Chengshuai Zhao, Raha Moraffah, Huan Liu
Keywords(s): Artificial Intelligence, Data Mining, Large Language Models, Machine Learning, Natural Language Processing
Category(s): Artificial Intelligence/Machine Learning, Cybersecurity, Computing & Information Technology, Intelligence & Security, Physical Science
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: 9/15/2025   |   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
Adversarial Text Purification: Large Language Model Approach for Defense
Background Adversarial purification is a defense mechanism for safe-guarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques analyze and eliminate adversarial perturbations from the attacked inputs, and help to restore purified samples that retain similarity to the attacked...
Published: 6/27/2025   |   Inventor(s): Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu
Keywords(s): Artificial Intelligence, Defense Applications, Machine Learning, Natural Language Processing, Security, Text Mining
Category(s): Physical Science, Artificial Intelligence/Machine Learning, Applied Technologies, Cybersecurity