DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with
Differentially Private Data Augmentations

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

2 March 2021

Valeriia Cherepanova

Furong Huang

Papers citing "DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations"

11 / 11 papers shown

Title
Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise Kyle Rui Sang Tahseen Rabbani Furong Huang FedML 36 0 0 20 Sep 2024
Does Federated Learning Really Need Backpropagation? H. Feng Tianyu Pang Chao Du Wei Chen Shuicheng Yan Min-Bin Lin FedML 36 10 0 28 Jan 2023
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks Tianwei Liu Yu Yang Baharan Mirzasoleiman AAML 30 27 0 14 Aug 2022
Fine-grained Poisoning Attack to Local Differential Privacy Protocols for Mean and Variance Estimation Xiaoguang Li Ninghui Li Wenhai Sun Neil Zhenqiang Gong Hui Li AAML 63 15 0 24 May 2022
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning Hao He Kaiwen Zha Dina Katabi AAML 34 32 0 22 Feb 2022
On the Effectiveness of Adversarial Training against Backdoor Attacks Yinghua Gao Dongxian Wu Jingfeng Zhang Guanhao Gan Shutao Xia Gang Niu Masashi Sugiyama AAML 32 22 0 22 Feb 2022
Adversarial Examples Make Strong Poisons Liam H. Fowl Micah Goldblum Ping Yeh-Chiang Jonas Geiping Wojtek Czaja Tom Goldstein SILM 32 132 0 21 Jun 2021
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch Hossein Souri Liam H. Fowl Ramalingam Chellappa Micah Goldblum Tom Goldstein SILM 31 124 0 16 Jun 2021
Survey: Image Mixing and Deleting for Data Augmentation Humza Naveed Saeed Anwar Munawar Hayat Kashif Javed Ajmal Mian 38 78 0 13 Jun 2021
AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning Yusuke Koda Jihong Park M. Bennis Praneeth Vepakomma Ramesh Raskar 21 10 0 02 May 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild D. Song A. Madry Bo-wen Li Tom Goldstein SILM 27 270 0 18 Dec 2020