47 citations · 73 across the 7 of their papers we have counts for
4 papers · 1 filter
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…