About

Hello! I recently completed a PhD in Mathematics at the University of Maryland co-advised by Professor Tom Goldstein (CS) and Professor Wojtek Czaja (Math). My research primarily focused on robustness and security for deep learning models. Specifically, I have worked on adversarial robustness, data poisoning attacks on deep networks, and, more recently, privacy attacks against both language and vision models trained in a federated learning setting.

Research Highlights

	Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. ICLR 2022 Liam Fowl, Jonas Geiping, Wojtek Czaja, Micah Goldblum, Tom Goldstein.
	Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. Preprint 2022 Liam Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojtek Czaja, Micah Goldblum, Tom Goldstein.
	Adversarial Examples Make Strong Poisons. NeurIPS 2021 Liam Fowl, Micah Goldblum, Ping-yeh Chiang*, Jonas Geiping, Wojtek Czaja, Tom Goldstein.
	Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching. ICLR 2021 Jonas Geiping, Liam Fowl, Ronny Huang, Wojtek Czaja, Gavin Taylor, Tom Goldstein.
	Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. ICML 2022 Yuxin Wen, Jonas Geiping, Liam Fowl*, Micah Goldblum, Tom Goldstein.
	Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch. Neurips 2022 (accepted for publication) Hossein Souri, Liam Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein.
	Adversarially Robust Few-Shot Learning: A Meta-Learning Approach. NeurIPS 2020 Micah Goldblum, Liam Fowl, Tom Goldstein.
	Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective CVPR 2022 (Oral) Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping Yeh-Chiang, Yehuda Dar, Richard Baraniuk, Micah Goldblum, Tom Goldstein.
	MetaPoison: Practical General-purpose Clean-label Data Poisoning. NeurIPS 2020 Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein.
	Adversarially Robust Distillation. AAAI 2020 Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein.

	Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. ICLR 2022 Liam Fowl, Jonas Geiping, Wojtek Czaja, Micah Goldblum, Tom Goldstein.
	Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. Preprint 2022 Liam Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojtek Czaja, Micah Goldblum, Tom Goldstein.
	Adversarial Examples Make Strong Poisons. NeurIPS 2021 Liam Fowl, Micah Goldblum, Ping-yeh Chiang*, Jonas Geiping, Wojtek Czaja, Tom Goldstein.
	Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching. ICLR 2021 Jonas Geiping, Liam Fowl, Ronny Huang, Wojtek Czaja, Gavin Taylor, Tom Goldstein.
	Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. ICML 2022 Yuxin Wen, Jonas Geiping, Liam Fowl*, Micah Goldblum, Tom Goldstein.
	Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch. Neurips 2022 (accepted for publication) Hossein Souri, Liam Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein.
	Adversarially Robust Few-Shot Learning: A Meta-Learning Approach. NeurIPS 2020 Micah Goldblum, Liam Fowl, Tom Goldstein.
	Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective CVPR 2022 (Oral) Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping Yeh-Chiang, Yehuda Dar, Richard Baraniuk, Micah Goldblum, Tom Goldstein.
	MetaPoison: Practical General-purpose Clean-label Data Poisoning. NeurIPS 2020 Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein.
	Adversarially Robust Distillation. AAAI 2020 Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein.