Knowledge Commons of Institute of Automation,CAS
Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks | |
Kai-Yuan Liu1,3; Xing-Yu Li2; Yu-Rui Lai1; Hang Su1; Jia-Chen Wang1; Chun-Xu Guo1; Hong Xie5,6; Ji-Song Guan1; Yi Zhou4 | |
发表期刊 | Machine Intelligence Research
![]() |
ISSN | 2731-538X |
2022 | |
卷号 | 19期号:5页码:456-471 |
摘要 | Despite its great success, deep learning severely suffers from robustness; i.e., deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the denoised internal models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired by the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness on the MNIST (Modified National Institute of Standards and Technology) dataset. |
关键词 | Brain-inspired learning autoencoder robustness adversarial attack generative model |
DOI | 10.1007/s11633-022-1375-7 |
七大方向——子方向分类 | 其他 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
中文导读 | https://mp.weixin.qq.com/s/ZqPI_moUsuRYLWOkI9r1gQ |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/55956 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.School of Life Sciences and Technology, ShanghaiTech University, Shanghai 201210, China 2.Shanghai Center for Brain Science and Brain-inspired Technology, Shanghai 201602, China 3.School of Life Sciences, Tsinghua University, Beijing 100084, China 4.National Engineering Laboratory for Brain-inspired Intelligence Technology and Application, School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China 5.Institute of Photonic Chips, University of Shanghai for Science and Technology, Shanghai 200093, China 6.Centre for Artificial-intelligence Nanophotonics, School of Optical-electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China |
推荐引用方式 GB/T 7714 | Kai-Yuan Liu,Xing-Yu Li,Yu-Rui Lai,et al. Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks[J]. Machine Intelligence Research,2022,19(5):456-471. |
APA | Kai-Yuan Liu.,Xing-Yu Li.,Yu-Rui Lai.,Hang Su.,Jia-Chen Wang.,...&Yi Zhou.(2022).Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks.Machine Intelligence Research,19(5),456-471. |
MLA | Kai-Yuan Liu,et al."Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks".Machine Intelligence Research 19.5(2022):456-471. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2022-04-114.pdf(3203KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论