Evolutionary Antivirus Signature Optimization
Eliana Giovannitti, Luca Mannella, Andrea Marcelli, Giovanni Squillero · 2019
This work presents a methodology to improve machine-generated signatures for Android Malware detection. The technique relies on a population-less evolutionary algorithm and uses an unorthodox fitness function that incorporates unsystematic human expert knowledge in the form of a set of rules of thumb. The proposed optimization algorithm does not require to rank the individuals and the resulting population of candidate solutions is not a totally ordered set. Experimental results show that the optimized signatures are more accurate than the original ones, lowering both false positives and false negatives.