Poisoned classifiers are not only backdoored, they are fundamentally
broken

Poisoned classifiers are not only backdoored, they are fundamentally broken

18 October 2020

Siddhant Agarwal

J. Zico Kolter

Papers citing "Poisoned classifiers are not only backdoored, they are fundamentally broken"

6 / 6 papers shown

Title
Trigger Hunting with a Topological Prior for Trojan Detection Xiaoling Hu Xiaoyu Lin Michael Cogswell Yi Yao Susmit Jha Chao Chen AAML 24 46 0 15 Oct 2021
Backdoor Attacks on Self-Supervised Learning Aniruddha Saha Ajinkya Tejankar Soroush Abbasi Koohpayegani Hamed Pirsiavash SSL AAML 27 101 0 21 May 2021
Manipulating SGD with Data Ordering Attacks Ilia Shumailov Zakhar Shumaylov Dmitry Kazhdan Yiren Zhao Nicolas Papernot Murat A. Erdogdu Ross J. Anderson AAML 112 91 0 19 Apr 2021
TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation Todd P. Huster E. Ekwedike SILM 36 19 0 18 Mar 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
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 296 3,112 0 04 Nov 2016