Most　existing　image　quality　assessment　(IQA)　methods　focus　on　improving　the　performance　of　synthetic　distorted　images.　Although　these　methods　perform　well　on　the　synthetic　distorted　IQA　database,　once　they　are　applied　to　the　natural　distorted　database,　the　performance　will　severely　decrease.　In　this　work,　we　propose　a　blind　image　quality　assessment　based　on　generative　adversarial　network　(BIQA-GAN)　with　its　advantages　of　self-generating　samples　and　self-feedback　training　to　improve　network　performance.　Three　different　BIQA-GAN　models　are　designed　according　to　the　target　domain　of　the　generator.　Comprehensive　experiments　on　popular　benchmarks　show　that　our　proposed　method　significantly　outperforms　the　previous　state-of-the-art　methods　for　authentically　distorted　images,　which　also　has　good　performances　on　synthetic　distorted　benchmarks.　©　2019　IEEE.