Picture for Blake Bullwinkel

Blake Bullwinkel

PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System

Add code
Oct 01, 2024
Viaarxiv icon

Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle

Add code
Jul 18, 2024
Figure 1 for Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Figure 2 for Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Figure 3 for Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Figure 4 for Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Viaarxiv icon

Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows

Add code
Nov 01, 2022
Viaarxiv icon

DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks

Add code
Sep 15, 2022
Figure 1 for DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
Figure 2 for DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
Figure 3 for DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
Figure 4 for DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
Viaarxiv icon

Evaluating the Fairness Impact of Differentially Private Synthetic Data

Add code
May 09, 2022
Figure 1 for Evaluating the Fairness Impact of Differentially Private Synthetic Data
Figure 2 for Evaluating the Fairness Impact of Differentially Private Synthetic Data
Figure 3 for Evaluating the Fairness Impact of Differentially Private Synthetic Data
Viaarxiv icon