Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks

15 July 2024

Lukas Gosch

Mahalakshmi Sabanayagam

Debarghya Ghoshdastidar

Stephan Günnemann

AAML

ArXiv (abs)PDF HTML

Papers citing "Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks"

23 / 23 papers shown

Title
Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising Sanghyun Hong Nicholas Carlini Alexey Kurakin DiffM 70 4 0 18 Mar 2024
Revisiting Robustness in Graph Machine Learning Lukas Gosch Daniel Sturm Simon Geisler Stephan Günnemann AAML OOD 117 23 0 01 May 2023
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks Keivan Rezaei Kiarash Banihashem Atoosa Malemir Chegini Soheil Feizi AAML 52 18 0 05 Feb 2023
Certifying Robustness to Programmable Data Bias in Decision Trees Anna P. Meyer Aws Albarghouthi Loris Dántoni 50 21 0 08 Oct 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild Basel Alomair Aleksander Madry Yue Liu Tom Goldstein SILM 90 281 0 18 Dec 2020
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks Jinyuan Jia Yupei Liu Xiaoyu Cao Neil Zhenqiang Gong AAML 75 74 0 07 Dec 2020
On the linearity of large non-linear models: when and why the tangent kernel is constant Chaoyue Liu Libin Zhu M. Belkin 106 142 0 02 Oct 2020
Simple and Deep Graph Convolutional Networks Ming Chen Zhewei Wei Zengfeng Huang Bolin Ding Yaliang Li GNN 119 1,486 0 04 Jul 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 216 1,846 0 03 Mar 2020
Spam Review Detection with Graph Convolutional Networks Ao Li Zhou Qin Runshi Liu Yiqun Yang Dong Li GNN 64 245 0 22 Aug 2019
Certifiable Robustness and Robust Training for Graph Convolutional Networks Daniel Zügner Stephan Günnemann OffRL 70 162 0 28 Jun 2019
Adversarial Attacks on Graph Neural Networks via Meta Learning Daniel Zügner Stephan Günnemann OOD AAML GNN 126 572 0 22 Feb 2019
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 152 2,044 0 08 Feb 2019
Predict then Propagate: Graph Neural Networks meet Personalized PageRank Johannes Klicpera Aleksandar Bojchevski Stephan Günnemann GNN 222 1,688 0 14 Oct 2018
How Powerful are Graph Neural Networks? Keyulu Xu Weihua Hu J. Leskovec Stefanie Jegelka GNN 243 7,653 0 01 Oct 2018
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning Matthew Jagielski Alina Oprea Battista Biggio Chang-rui Liu Cristina Nita-Rotaru Yue Liu AAML 85 761 0 01 Apr 2018
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization Luis Muñoz-González Battista Biggio Ambra Demontis Andrea Paudice Vasin Wongrassamee Emil C. Lupu Fabio Roli AAML 99 633 0 29 Aug 2017
Certified Defenses for Data Poisoning Attacks Jacob Steinhardt Pang Wei Koh Percy Liang AAML 97 755 0 09 Jun 2017
Inductive Representation Learning on Large Graphs William L. Hamilton Z. Ying J. Leskovec 509 15,247 0 07 Jun 2017
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 213 2,894 0 14 Mar 2017
OptNet: Differentiable Optimization as a Layer in Neural Networks Brandon Amos J. Zico Kolter 158 963 0 01 Mar 2017
Semi-Supervised Classification with Graph Convolutional Networks Thomas Kipf Max Welling GNN SSL 641 29,076 0 09 Sep 2016
Poisoning Attacks against Support Vector Machines Battista Biggio B. Nelson Pavel Laskov AAML 112 1,590 0 27 Jun 2012