Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification
Authors: Chuanshuai Chen, Jiazhu Dai | Published: 2020-07-11 | Updated: 2021-03-15
AIセキュリティポータルbot
Generating Adversarial Inputs Using A Black-box Differential Technique
Authors: João Batista Pereira Matos Juúnior, Lucas Carvalho Cordeiro, Marcelo d'Amorim, Xiaowei Huang | Published: 2020-07-10
Differentially Private Simple Linear Regression
Authors: Daniel Alabi, Audra McMillan, Jayshree Sarathy, Adam Smith, Salil Vadhan | Published: 2020-07-10
Improving Adversarial Robustness by Enforcing Local and Global Compactness
Authors: Anh Bui, Trung Le, He Zhao, Paul Montague, Olivier deVel, Tamas Abraham, Dinh Phung | Published: 2020-07-10
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
Authors: Hongyi Wang, Kartik Sreenivasan, Shashank Rajput, Harit Vishwakarma, Saurabh Agarwal, Jy-yong Sohn, Kangwook Lee, Dimitris Papailiopoulos | Published: 2020-07-09
Evaluation of Adversarial Training on Different Types of Neural Networks in Deep Learning-based IDSs
Authors: Rana Abou Khamis, Ashraf Matrawy | Published: 2020-07-08
On the relationship between class selectivity, dimensionality, and robustness
Authors: Matthew L. Leavitt, Ari S. Morcos | Published: 2020-07-08 | Updated: 2020-10-13
How benign is benign overfitting?
Authors: Amartya Sanyal, Puneet K Dokania, Varun Kanade, Philip H. S. Torr | Published: 2020-07-08
BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning
Authors: Vaikkunth Mugunthan, Ravi Rahman, Lalana Kagal | Published: 2020-07-08
Defending against Backdoors in Federated Learning with Robust Learning Rate
Authors: Mustafa Safa Ozdayi, Murat Kantarcioglu, Yulia R. Gel | Published: 2020-07-07 | Updated: 2021-07-29