70 citations · 117 across the 10 of their papers we have counts for
10 papers
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
Duong M. Nguyen, Joon Sik Kim, Blazej Manczak +1
We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this…
Assisting Human Decisions in Document Matching
Joon Sik Kim, Valerie Chen, Danish Pruthi +2
Many practical applications, ranging from paper-reviewer assignment in peer review to job-applicant matching for hiring, require human decision makers to identify relevant matches…
Bayesian Persuasion for Algorithmic Recourse
Keegan Harris, Valerie Chen, Joon Sik Kim +3
When subjected to automated decision-making, decision subjects may strategically modify their observable features in ways they believe will maximize their chances of receiving a fa…
Sanity Simulations for Saliency Methods
Joon Sik Kim, Gregory Plumb, Ameet Talwalkar
Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input ima…
Interpretable Machine Learning: Moving From Mythos to Diagnostics
Valerie Chen, Jeffrey Li, Joon Sik Kim +2
Despite increasing interest in the field of Interpretable Machine Learning (IML), a significant gap persists between the technical objectives targeted by researchers' methods and t…
FACT: A Diagnostic for Group Fairness Trade-offs
Joon Sik Kim, Jiahao Chen, Ameet Talwalkar
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conf…
PLLay: Efficient Topological Layer based on Persistence Landscapes
Kwangho Kim, Jisu Kim, Manzil Zaheer +3
We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological feature…
Automated Dependence Plots
David I. Inouye, Liu Leqi, Joon Sik Kim +2
In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model.…
Representer Point Selection for Explaining Deep Neural Networks
Chih-Kuan Yeh, Joon Sik Kim, Ian E. H. Yen +1
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Sp…
A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses
Matteo Ruggero Ronchi, Joon Sik Kim, Yisong Yue
We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The m…