chandlerbang/awesome-graph-attack-papers

Adversarial attacks and defenses on Graph Neural Networks.

awesome-graph-attack-papers's Issues

Add a relevant paper

Hi Dr. Wei Jin,

Thanks for maintaining this awesome repo!

I would like to add our work (as follows) to this repo, which is quite relevant.

• Paper: On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
• PDF: https://arxiv.org/pdf/2306.09104.pdf
• Code: https://github.com/tmlr-group/MC-GRA

Thanks for your attention.

Best Regards,
Zhanke

Add a defense paper

It would be great if you can add our recent paper covering a scalable defense accepted by Learning on Graphs (LoG) 2022:
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks [paper] [code] by Chenhui Deng, Xiuyu Li, Zhuo Feng, Zhiru Zhang

Thank you!

Add attack paper

Hi,

it would be great if you could list our recent workshop paper:

Simon Geisler (Technical University of Munich)*; Daniel Zügner (Technical University of Munich); Aleksandar Bojchevski (Technical University of Munich); Stephan Günnemann (Technical University of Munich). Attacking Graph Neural Networks at Scale

That would be awesome! Thanks in advance and for maintaining this helpful overview!

Are you available for freelancing?

@ChandlerBang
Hi there,
i have a task that i want to solve using machine learning,
are you interested in freelancing?

what is your email so that i can discuss with you with details,
waiting for your reply

Please add our new backdoor attack paper by RAID 2022

Hi @ChandlerBang,

It will be great if you can add our latest graph backdoor paper accepted by RAID 2022,

"Transferable Graph Backdoor Attack. Shuiqiao Yang, Bao Gia Doan, Paul Montague, Olivier De Vel, Tamas Abraham, Seyit Camtepe, Damith C. Ranasinghe, Salil S. Kanhere"

URL: https://arxiv.org/abs/2207.00425
Thanks.

Please add our two new papers

Robustness of Graph Neural Networks at Scale

Covering two scalable attacks (both local/global or I think you call it targeted/untargeted) and one defense.

https://www.in.tum.de/daml/robustness-of-gnns-at-scale/

@inproceedings{geisler2021_robustness_of_gnns_at_scale,
title = {Robustness of Graph Neural Networks at Scale},
author = {Tobias Schmidt, Hakan \c{S}irin, DanielZ"ugner, Aleksandar Bojchevski, and StephanG"unnemann},
booktitle={Neural Information Processing Systems, {NeurIPS}},
year = {2021}
}

Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness

Adversarial attacks on neural solvers for TSP and SAT.

https://arxiv.org/abs/2110.10942

Thanks :-)

Two new robustness certificates

Hi! Thanks a lot for curating this very helpful collection of graph adversarial robustness papers.

I wanted to ask if you could add the following two certificate papers from our group (the second one can be applied to various tasks, but is especially effective for graph neural networks).

https://www.cs.cit.tum.de/daml/interception-smoothing

 @inproceedings{scholten2022interception_smoothing,
    title = {Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks},
    author = {Scholten, Yan and Schuchardt, Jan and Geisler, Simon and Bojchevski, Aleksandar and G{\"u}nnemann, Stephan},
    booktitle={Neural Information Processing Systems, {NeurIPS}},
    year = {2022}
    }

and

https://openreview.net/forum?id=-k7Lvk0GpBl

   @inproceedings{schuchardt2023localized_smoothing,
    title = {Localized Randomized Smoothing for Collective Robustness Certification},
    author = {Schuchardt, Jan and Wollschl\"ager, Tom and Bojchevski, Aleksandar and G{\"u}nnemann, Stephan},
    booktitle={International Conference on Learning Representations, {ICLR}},
    year = {2023}
    }