Black-box reversible adversarial examples with invertible neural network

Jielun Huang, Guoheng Huang, Xuhui Zhang, Xiaochen Yuan, Fenfang Xie, Chi-Man Pun, Guo Zhong

Abstract: Highlights•The proposed I-RAE scheme focuses on black-box Reversible Adversarial Example (RAE) generation.•The proposed I-RAE applies invertible neural network for generation.•The proposed I-RAE reduces the embedding loss during RAE generation.•The proposed I-RAE outperforms other RAE schemes.