47 citations · 73 across the 7 of their papers we have counts for
7 papers
Jailbreaking Black Box Large Language Models in Twenty Queries
Patrick Chao, Alexander Robey, Edgar Dobriban +3
There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, whic…
Minimax Statistical Estimation under Wasserstein Contamination
Patrick Chao, Edgar Dobriban
Contaminations are a key concern in modern statistical learning, as small but systematic perturbations of all datapoints can substantially alter estimation results. Here, we study…
Black Box Adversarial Prompting for Foundation Models
Natalie Maus, Patrick Chao, Eric Wong +1
Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to…
Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries
Patrick Chao, Patrick Blöbaum, Sapan Patel +1
We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph a…
AdaPT-GMM: Powerful and robust covariate-assisted multiple testing
Patrick Chao, William Fithian
We propose a new empirical Bayes method for covariate-assisted multiple testing with false discovery rate (FDR) control, where we model the local false discovery rate for each hypo…
Generative Models for Pose Transfer
Patrick Chao, Alexander Li, Gokul Swamy
We investigate nearest neighbor and generative models for transferring pose between persons. We take in a video of one person performing a sequence of actions and attempt to genera…
The Stochastic Replica Approach to Machine Learning: Stability and Parameter Optimization
Patrick Chao, Tahereh Mazaheri, Bo Sun +2
We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of…