Some Submodular Data-Poisoning Attacks on Machine Learners

By Shike Mei, Xiaojin Zhu. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jy-yong Sohn
2. Dimitris Papailiopoulos
3. Hongyi Wang
4. Shashank Rajput
5. Kangwook Lee
6. Kartik K. Sreenivasan
7. Harit Vishwakarma
8. Saurabh Agarwal

Citations in the corpus

• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “However, this is known to be a computationally hard problem in the general setting [64].”
• A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples (2016, background): “Multiple recent papers (Alfeld et al., 2016; Mei & Zhu, 2015b; Biggio et al., 2014; 2012; Mei & Zhu, 2015a) have considered the problem of an adversary being able to pollute the training data with the goal of influencing learning systems including support vector machines (SVM), autoregressive models…”