CASIA OpenIR

浏览/检索结果: 共58条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
基于通用逆扰动的对抗攻击防御方法 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 10, 页码: 2172-2187
作者:  陈晋音;  吴长安;  郑海斌;  王巍;  温浩
Adobe PDF(11578Kb)  |  收藏  |  浏览/下载:3/1  |  提交时间:2024/04/24
深度学习  通用逆扰动  对抗样本  通用防御  
Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 5, 页码: 666-682
作者:  Cheng-Cheng Ma;  Bao-Yuan Wu;  Yan-Bo Fan;  Yong Zhang;   Zhi-Feng Li
Adobe PDF(9598Kb)  |  收藏  |  浏览/下载:5/1  |  提交时间:2024/04/23
Adversarial defense, adversarial detection, generalized Gaussian distribution, Benford-Fourier coefficients, image classification  
Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 2, 页码: 180-193
作者:  Zhengyan Zhang;  Guangxuan Xiao;  Yongwei Li;  Tian Lv;  Fanchao Qi;  Zhiyuan Liu;  Yasheng Wang;  Xin Jiang;  Maosong Sun
Adobe PDF(1649Kb)  |  收藏  |  浏览/下载:5/3  |  提交时间:2024/04/23
Pre-trained language models  backdoor attacks  transformers  natural language processing (NLP)  computer vision (CV)  
Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 5, 页码: 456-471
作者:  Kai-Yuan Liu;  Xing-Yu Li;  Yu-Rui Lai;  Hang Su;  Jia-Chen Wang;  Chun-Xu Guo;  Hong Xie;  Ji-Song Guan;  Yi Zhou
Adobe PDF(3203Kb)  |  收藏  |  浏览/下载:1/0  |  提交时间:2024/04/23
Brain-inspired learning  autoencoder  robustness  adversarial attack  generative model  
Towards Interpretable Defense Against Adversarial Attacks via Causal Inference 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 3, 页码: 209-226
作者:  Min Ren;  Yun-Long Wang;  Zhao-Feng He
Adobe PDF(5143Kb)  |  收藏  |  浏览/下载:1/0  |  提交时间:2024/04/23
Adversarial sample  adversarial defense  causal inference  interpretable machine learning  transformers  
针对身份证文本识别的黑盒攻击算法研究 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 1, 页码: 103-120
作者:  徐昌凯;  冯卫栋;  张淳杰;  郑晓龙;  张辉;  王飞跃
Adobe PDF(20872Kb)  |  收藏  |  浏览/下载:27/13  |  提交时间:2024/04/12
对抗样本  黑盒攻击  身份证文本识别  物理世界  二值化掩码  
Cybersecurity Landscape on Remote State Estimation: A Comprehensive Review 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 4, 页码: 851-865
作者:  Jing Zhou;  Jun Shang;  Tongwen Chen
Adobe PDF(1169Kb)  |  收藏  |  浏览/下载:17/4  |  提交时间:2024/03/18
Cyber-attacks  Kalman filtering  remote state estimation  unreliable transmission channels  
Achieving 500X Acceleration for Adversarial Robustness Verification of Tree-Based Smart Grid Dynamic Security Assessment 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 3, 页码: 800-802
作者:  Chao Ren;  Chunran Zou;  Zehui Xiong;  Han Yu;  Zhao-Yang Dong;  Niyato Dusit
Adobe PDF(469Kb)  |  收藏  |  浏览/下载:71/27  |  提交时间:2024/02/19
Advancements in Humanoid Robots: A Comprehensive Review and Future Prospects 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 2, 页码: 301-328
作者:  Yuchuang Tong;  Haotian Liu;  Zhengtao Zhang
Adobe PDF(7587Kb)  |  收藏  |  浏览/下载:73/14  |  提交时间:2024/01/23
Future trends and challenges  humanoid robots  human-robot interaction  key technologies  potential applications  
面向文本理解的对抗攻防方法研究 学位论文
, 2023
作者:  施家辉
Adobe PDF(3860Kb)  |  收藏  |  浏览/下载:127/4  |  提交时间:2023/09/27
对抗攻击  对抗样本  对抗防守  深度神经网络  自然语言处理