Wentao Zhao1, Pan Li1,*, Chengzhang Zhu1,2, Dan Liu1, Xiao Liu1
CMC-Computers, Materials & Continua, Vol.59, No.3, pp. 817-832, 2019, DOI:10.32604/cmc.2019.05957
Abstract The defense techniques for machine learning are critical yet challenging due to the number and type of attacks for widely applied machine learning algorithms are significantly increasing. Among these attacks, the poisoning attack, which disturbs machine learning algorithms by injecting poisoning samples, is an attack with the greatest threat. In this paper, we focus on analyzing the characteristics of positioning samples and propose a novel sample evaluation method to defend against the poisoning attack catering for the characteristics of poisoning samples. To capture the intrinsic data characteristics from heterogeneous aspects, we first evaluate training data More >
Login
Register
