Membership Inference Attack for beluga whales discrimination

Voncarlos Macelo de Araújo, Ankita Shukla, Sébastien Gambs, Clément Chion, Robert Michaud

To efficiently monitor the growth and evolution of a particular wildlife population, one of the main fundamental challenges to address in animal ecology is the re-identification of individuals that have been previously encountered but also the discrimination between known and unknown individuals (the so-called “open-set problem”), which is the first step to realize before re-identification. In particular, in this work, we are interested in the discrimination within digital photos of beluga whales, which are known to be among the most challenging marine species to discriminate due to their lack of distinctive features. To tackle this problem, we propose a novel approach based on the use of Membership Inference Attacks (MIAs), which are normally used to assess the privacy risks associated with releasing a particular ma- chine learning model. More precisely, we demonstrate that the problem of discriminating between known and unknown individuals can be solved efficiently using state-of-the-art ap- proaches for MIAs. Extensive experiments on three benchmark datasets related to whales, two different neural network architectures, and three MIA clearly demonstrate the performance of the approach. In addition, we have also de- signed a novel MIA strategy that we coined as ensemble MIA, which combines the outputs of different MIAs to in- crease the attack accuracy while diminishing the false pos- itive rate. Overall, one of our main objectives is also to show that the research on privacy attacks can also be leveraged “for good” by helping to address practical challenges encountered in animal ecology.