Liam H Fowl

Google, Google

Joined

September 2019

Names

Liam H Fowl (Preferred)

Liam Fowl

Liam H. Fowl

Emails

****@math.umd.edu (Confirmed)

****@gmail.com (Confirmed)

****@umd.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Google

Google (google.com)

2022 – Present

PhD student

University of Maryland, College Park (umd.edu)

2016 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Tom Goldstein

Present

Expertise

Deep Learning

2016 – 2022

Robustness

2016 – 2022

Harmonic Analysis

2016 – 2020

Publications

DP-InstaHide: Data Augmentations Provably Enhance Guarantees Against Dataset Manipulations
Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam H Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein
- Published: 05 Dec 2022, Last Modified: 05 May 2023
- MLSW2022
- Readers: Everyone
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Liam H Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojciech Czaja, Micah Goldblum, Tom Goldstein
- Published: 05 Dec 2022, Last Modified: 15 Feb 2026
- MLSW2022
- Readers: Everyone
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
Hong-Min Chu, Jonas Geiping, Liam H Fowl, Micah Goldblum, Tom Goldstein
- Published: 05 Dec 2022, Last Modified: 05 May 2023
- MLSW2022
- Readers: Everyone
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Liam H Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojciech Czaja, Micah Goldblum, Tom Goldstein
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- ICLR 2023 poster
- Readers: Everyone
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
Hong-Min Chu, Jonas Geiping, Liam H Fowl, Micah Goldblum, Tom Goldstein
- Published: 01 Feb 2023, Last Modified: 01 Mar 2023
- ICLR 2023 poster
- Readers: Everyone
DP-InstaHide: Data Augmentations Provably Enhance Guarantees Against Dataset Manipulations
Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam H Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
Yuxin Wen, Jonas Geiping, Liam H Fowl, Hossein Souri, Rama Chellappa, Micah Goldblum, Tom Goldstein
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
Hossein Souri, Liam H Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Poisons that are learned faster are more effective
Pedro Sandoval Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein
- 2022 (modified: 01 Nov 2022)
- CVPR Workshops 2022
- Readers: Everyone
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
Yuxin Wen, Jonas Geiping, Liam Fowl, Hossein Souri, Rama Chellappa, Micah Goldblum, Tom Goldstein
- 2022 (modified: 02 Nov 2022)
- CoRR 2022
- Readers: Everyone

View all 55 publications

Co-Authors

View all 50 co-authors