3 papers
cs.CR2026
Quantifiable Uncertainty: A Stochastic Consensus Multi-Agent RAG Framework for Robust Malware Detection
ElMouatez Billah Karbab
While contemporary deep learning malware detectors define a dominant defense paradigm, their sophistication also exposes them to novel structural evasion attacks, a limitation we a…
cs.CR2026
Applying Graph Analysis for Unsupervised Fast Malware Fingerprinting
ElMouatez Billah Karbab, Mourad Debbabi
Malware proliferation is increasing at a tremendous rate, with hundreds of thousands of new samples identified daily. Manual investigation of such a vast amount of malware is an un…
cs.CR2026
AsmRAG: LLM-Driven Malware Detection by Retrieving Functionally Similar Assembly Code
ElMouatez Billah Karbab
Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack foren…