The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
No Time to Evade: Context-Aware Conditional Entropy Partitioning and Model Fusion for Robust Multiprocess Malware Detection
- Published
- Record updated
Summary
Malware detectors trained on single-process system call traces generalize poorly against polymorphic evasion that splits tasks across threads and processes. The authors propose an entropy-based partitioning of system call logs with a violation-aware penalty that preserves temporal and semantic dependencies, combined with ensemble fusion of submodels trained under heterogeneous adversarial split configurations. Evaluated on ADFA-LD, ADFA-LD-MP and the BarongTrace dataset, the framework reports improved F1-scores, particularly in high-split regimes where conventional models degrade.