Scholar
Luke Bailey
Google Scholar ID: ry4HY8cAAAAJ
Stanford University
Citations & Impact
Citations
766
H-index
7
i10-index
6
Publications
10
Co-authors
0
Contact
Publications
Cited
0
Resume (English only)
Academic Achievements
- Paper: Obfuscated Activations Bypass LLM Latent-Space Defenses (arXiv, 2024)
- Paper: Failures to Find Transferable Image Jailbreaks Between Vision-Language Models (arXiv, 2024, Best Paper Award @ Neurips RBFM Workshop 2024)
- Paper: Image Hijacks: Adversarial Images can Control Generative Models at Runtime (ICML, 2024)
- Paper: Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game (ICLR, 2024, Spotlight)
- Paper: A Petavoxel Fragment of Human Cerebral Cortex Reconstructed at Nanoscale Resolution (Science, 2024)
- Paper: Soft Prompting Might be a Bug, Not a Feature (ICML Workshop on Deployment Challenges for Generative AI, 2023)
- Paper: SpeedLimit: Neural Architecture Search for Quantized Transformer Models (ICML Workshop on Efficient Systems for Foundation Models, 2023)
- Paper: CoopMC: Algorithm-architecture Co-optimization for Markov Chain Monte Carlo Accelerators (IEEE HPCA, 2022)
Background
- First year Computer Science PhD student at Stanford University, interested in making AI models safer and more robust.
Miscellany
- Personal interests not mentioned
Co-authors