tuananhbui89 / AML-Leaders

Personal list of researchers or groups in the field of Adversarial Machine Learning

AML-Leaders

Disclaimer

This is a list of research groups and notable researchers in the field of Adversarial Machine Learning that I personally find interesting. It is important to note that this list is by no means exhaustive, nor is it intended to serve as a definitive ranking. Its purpose was to provide a curated selection of resources for reference or exploration (I was searching for an internship :). Therefore, please be gentle with me, any suggestions are welcome.

Groups or leaders and their useful resources

The Table below can be found in AML-People-Group.csv and is generated by the command

python gentable.py

Name	Affilation	Resources
Bethge Lab	Tubingen	Foolbox
TrustworthyML Initiative	Harvard
Gradient Science Lab	MIT	AML in practice
BoLi Lab	UIUC, UC Berkeley
Princeton-AML Group	Princeton
Q Data (Yanjun Qi)	Uni of Virginia	Text Attack
Machine Learning Security	University of Cagliari, Italy
Nicholas Carlini	Google, UC Berkeley	C&W Attacks, How to evaluate Adversarial Robustness A Complete List of All Adversarial Example Papers Adversarial Machine Learning Reading List
Nicolas Papernot	UoT, PenState	Differential Privacy Cleverhans
Ian Goodfellow	Apple, Montreal	FGSM Cleverhans
Dawn Song	UC Berkeley
Aleksander Madry	MIT	PGD
Alex Beutel	Google	Recommender, Fairness
Colin Raffe	Google, Uni of North Carolina, Chapel Hill, Hugging Face	Building Machine Learning Models like Open-Source Software
Stefano Ermon	Stanford	GAN
Cihang Xie	UC Santa Cruz, John Hopkins
Reza Schokri	NUS
Gong Group	Duke
Kamalika Chaudhuri	UCSD
David Evans	Virginia
Jun Zhu	Tsinghua
Tianyu Pang	Sea AI Lab, Tsinghua
Yisen Wang	Peking
Florian Tramer	UTHZ, Stanford	Ensemble AT, Various inference attacks, adversarial examples, memorization in language models
Hongyang Zhang	Waterloo, TTIC	TRADES
Pin-Yu Chen	IBM	Tutorials, Workshops, Books on AML
Wieland Brendel	Max Planck, Tubingen
Jonas Rauber	Tubingen
Matthias Hein	Tubingen
Francesco Croce	Tubingen	Robustbench, Auto-Attack
Maksym Andriushchenko	EPFL	SAM
Haichao Zhange	Horizon
Anh Nguyen	Auburn	Visual explaination
Data Analytics Lab	ETHZ
Seyed Moosavi	ETHZ, UCL	Deepfool, Universal Perturbations
Chaowei Xiao	Nvidia
TrustingAI	IBM
Jianyu Wang	Waymo, UCLA
Huan Zhang	CMU, UCLA
Cho-Jui Hsieh	UCLA
DJ	Deepmind
Yisen Guo	ByteDance
Cheng Zhang	MSR
David Stutz	Tubingen, Deep mind
Yinpeng Dong	Tsinghua
Robert Geirhos	Google Brain, Tubingen	Shortcut learning
Zico Kolter	CMU	Certified Robustness
Eric Wong	CMU, UniPen	Certified Robustness
Percy Liang	Stanford	LLM
Xingjun Ma	Fudan Uni, UniMelb
Sven Gowal	Deepmind
Soheil Feizi	Maryland
Tom Goldstein	Maryland
Tsui-Wei Weng	MIT
Jinfeng Yi	IBM
Battista Biggio	University of Cagliari, Italy	Very first AML research
Christian szegedy	Google	Adversarial examples
Yao Qin	UCSB, Google
John Duchi	Stanford	Distributional Robustness
THUNLP	Tsinghua	Textual Attack and Defense
Maura Pintor	University of Cagliari, Italy
Kush Varshney	IBM	Trusthworthy ML book
Hima Lakkaraju	Harvard	TrustworthyML Initiative
Maria-Irina Nicolae	Bosch AI, IBM	Adversarial Robustness Toolbox
Micah Goldblum	NYU, Maryland
Jonas Geiping	Maryland

Some other statistics

The below statistics are generated from the data source in Carlini's blog post "A Complete List of All (arXiv) Adversarial Example Papers" using the notebook advex_papers_readers.ipynb in this repo.

Updated on 2023-06-01. There are total 7158 papers in the list.

Total individual authors: 18130
Total papers: 7158
Who has published most: Bo Li with 93 papers
Who has published most as first-author: Jinyin Chen with 20 papers

--- Top-10 authors ---
Bo Li 93
Pin-Yu Chen 84
Cho-Jui Hsieh 75
Jun Zhu 59
Sijia Liu 56
Hang Su 51
Yang Liu 46
Battista Biggio 44
Soheil Feizi 44
Huan Zhang 40

--- Top-10 first author ---
Jinyin Chen 20
Nicholas Carlini 18
Francesco Croce 13
Yinpeng Dong 13
Nicolas Papernot 11
Jinyuan Jia 10
Mingfu Xue 10
Chawin Sitawarin 10
Ali Borji 10
Muzammal Naseer 10

TODO

• Automatically search all affiliations and generate a list of affiliations. It would be helpful for people to find internships.