Luke Bailey
I am a first year Computer Science PhD student at Stanford University. I am supported by both a Stanford Graduate Fellowship, and a Future of Life Institute Vitalik Buterin Fellowship.
Previously, I completed a joint degree in Computer Science and Mathematics at Harvard University. During my undergraduate degree, I conducted research at the Harvard DtAK lab, advised by Weiwei Pan, Yaniv Yacoby, and Siddharth Swaroop. I also conducted research at the UC Berkeley Center for Human Compatible AI, advised by Scott Emmons.
I am interested in making AI models safer and more robust. If you are interested in collaborating, please reach out.
Email: ljbailey [at] stanford [dot] edu
Google Scholar
Papers
-
Obfuscated Activations Bypass LLM Latent-Space Defenses
Luke Bailey*, Alex Serrano*, Abhay Sheshadri*, Mikhail Seleznyov*, Jordan Taylor*, Erik Jenner*, Jacob Hilton, Stephen Casper, Carlos Guestrin, and Scott Emmons
arXiv, 2024
[arXiv | BibTeX] -
Failures to Find Transferable Image Jailbreaks
Between Vision-Language Models
Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristóbal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, and Ethan Perez
arXiv, 2024, Best Paper Award @ Neurips RBFM Workshop 2024
[arXiv | BibTeX] -
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
Luke Bailey*, Euan Ong*, Stuart Russell, and Scott Emmons
ICML, 2024
[arXiv | BibTeX] -
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Sam Toyer, Olivia Watkins, Ethan Adrian Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, Alan Ritter, and Stuart Russell
ICLR, 2024, Spotlight
[arXiv | BibTeX] -
A Petavoxel Fragment of Human Cerebral Cortex Reconstructed at Nanoscale Resolution
Alexander Shapson-Coe*, Michał Januszewski*, Daniel R. Berger*, Art Pope, Yuelong Wu,Tim Blakely, Richard L. Schalek, Peter H. Li, Shuohong Wang, Jeremy Maitin-Shepard, Neha Karlupia, Sven Dorkenwald, Evelina Sjostedt, Laramie Leavitt, Dongil Lee, Jakob Troidl, Forrest Collman, Luke Bailey, Angerica Fitzmaurice, Rohin Kar, Benjamin Field, Hank Wu, Julian Wagner-Carena,David Aley, Joanna Lau, Zudi Lin, Donglai Wei, Hanspeter Pfister, Adi Peleg, Viren Jain, and Jeff W. Lichtman
Science, 2024
[Science | BibTeX] -
Soft Prompting Might be a Bug, Not a Feature
Luke Bailey*, Gustaf Ahdritz*, Anat Kleiman*, Siddharth Swaroop, Finale Doshi-Velez, and Weiwei Pan
ICML Workshop on Deployment Challenges for Generative AI, 2023
[OpenReview | BibTeX] -
SpeedLimit: Neural Architecture Search for Quantized Transformer Models
Yuji Chai*, Luke Bailey*, Yunho Jin, Matthew Karle, Glenn Ko, David Brooks, Gu-Yeon Wei, and H. T. Kung
ICML Workshop on Efficient Systems for Foundation Models, 2023
[arXiv | BibTeX] -
CoopMC: Algorithm-architecture Co-optimization for Markov Chain Monte Carlo Accelerators
Yuji Chai, Glenn G. Ko, Wei-Te Mark Ting, Luke Bailey, David Brooks, and Gu-Yeon Wei
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2022
[IEEE | BibTeX]