Roozbeh Razavi-Far

The paper proposes a zero-label malware family classification framework that uses a weighted hierarchical ensemble of large language models (LLMs) to classify malware without requiring labeled training data.

The paper introduces LLM4CodeRE, a domain-adaptive LLM framework that significantly improves bidirectional code reverse engineering by unifying assembly-to-source and source-to-assembly translation.

This survey provides a detailed overview of quantum adversarial machine learning, examining existing attacks, novel quantum-enhanced defense strategies, and the theoretical challenges in securing quantum machine learning models.