MARD is a ReAct-based multi-agent LLM framework that detects Android malware at 93.46% F1 without fine-tuning and shows robustness to concept drift across five-year evaluations.
Cruparamer: Learning on parameter-augmented api sequences for malware detection.IEEE Transactions on Information Forensics and Security, 17:788–803
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MARD: A Multi-Agent Framework for Robust Android Malware Detection
MARD is a ReAct-based multi-agent LLM framework that detects Android malware at 93.46% F1 without fine-tuning and shows robustness to concept drift across five-year evaluations.