A Machine Learning-based Attack-Preventive Synthesis for Cyber-Physical DMFBs

A digital microfluidic biochip (DMFB) with cyber-physical adaptation is undeniably susceptible to attack due to high network connection. A number of leading researches are carried out to assess various attacks and their impacts. Several defence mechanisms are developed by arranging on-chip monitoring systems through deployment of checkpoints. However, the synthesis phase in DMFB plays a crucial role to realize a given bio-protocol by modelling it as a bioassay graph, placing mixing modules on the chip, and carrying out on-chip droplet routes. An attack-preventive synthesis that can execute a bioassay in a vulnerable environment is immensely important. Here, an attack-preventive synthesis is proposed that deals with denial-of-service attacks. A predictive model is developed following a machine learning-based approach to enable the synthesis phase for anticipating the impact of various attack scenarios. A probabilistic analysis is presented to measure safeness of a bioassay under an attack-prone scenario. The model is evaluated over a wide-ranged dataset.