Get started
Author

Blake Bullwinkel

Observed name: Bullwinkel, Blake
ORCID: 0009-0008-6623-8181
Observed ORCID: 0009-0008-6623-8181
OpenAlex ID: A5125092966
Evaluating the Fairness Impact of Differentially Private Synthetic Data
2022 · Bullwinkel, Blake, Grabarz, Kristen, et al. · arXiv (Cornell University) · 9
PDF
DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
2022 · Bullwinkel, Blake, Randle, Dylan, et al. · arXiv (Cornell University) · 6
PDF
Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows
2022 · Pellegrin, Raphaël, Bullwinkel, Blake, et al. · arXiv (Cornell University) · 4
PDF
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System
2024 · Munoz, Gary D. Lopez, Minnich, Amanda J., et al. · arXiv (Cornell University) · 2
PDF
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
2024 · Haider, Emman, Perez-Becker, Daniel, et al. · arXiv (Cornell University) · 2
PDF
Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs
2026 · Ningjing Tang, Alice Qian, et al. · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · 1
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
2025 · Bullwinkel, Blake, Russinovich, Mark, et al. · arXiv (Cornell University) · 1
PDF
Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations
2024 · Ma, Zilin, Susannah, et al. · arXiv (Cornell University) · 1
PDF
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
2026 · Russinovich, Mark, Bullwinkel, Blake, et al. · arXiv (Cornell University)
PDF
Evading Chain-of-Thought Monitoring Through Model Poisoning
2026 · Severi, Giorgio, Mirza, Shujaat, et al. · arXiv (Cornell University)
PDF
Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO
2026 · Bullwinkel, Blake, Kim, Eugenia, et al. · arXiv (Cornell University)
PDF
GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt
2026 · Russinovich, Mark, Cai, Yanan, et al. · arXiv (Cornell University)
PDF
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
2026 · Bullwinkel, Blake, Severi, Giorgio, et al. · arXiv (Cornell University)
PDF
Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs
2026 · Tang, Ningjing, Qian, Alice, et al. · arXiv (Cornell University)
PDF
A Systematization of Security Vulnerabilities in Computer Use Agents
2025 · Jones, Daniel, Severi, Giorgio, et al. · arXiv (Cornell University)
PDF
Works count: 16
Citation count: 28
H-index: 3
I10-index:
Year
Topic
Type