55 citations · 66 across the 13 of their papers we have counts for
14 papers
PolicyBank: Evolving Policy Understanding for LLM Agents
Jihye Choi, Jinsung Yoon, Long T. Le +2
LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably c…
ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
Jihye Choi, Jinsung Yoon, Jiefeng Chen +2
While Large Language Models (LLMs) have shown remarkable advancements in reasoning and tool use, they often fail to generate optimal, grounded solutions under complex constraints.…
SLVR: Securely Leveraging Client Validation for Robust Federated Learning
Jihye Choi, Sai Rahul Rachuri, Ke Wang +2
Federated Learning (FL) enables collaborative model training while keeping client data private. However, exposing individual client updates makes FL vulnerable to reconstruction at…
Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
Jihye Choi, Jayaram Raghuram, Yixuan Li +1
Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are l…
MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance
Jihye Choi, Nils Palumbo, Prasad Chalasani +4
In the era of Large Language Models (LLMs), given their remarkable text understanding and generation abilities, there is an unprecedented opportunity to develop new, LLM-based meth…
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Neal Mangaokar, Ashish Hooda, Jihye Choi +4
Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks th…
Why Train More? Effective and Efficient Membership Inference via Memorization
Jihye Choi, Shruti Tople, Varun Chandrasekaran +1
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and…
Identifying and Mitigating the Security Risks of Generative AI
Clark Barrett, Brad Boyd, Elie Burzstein +20
Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, s…
Stratified Adversarial Robustness with Rejection
Jiefeng Chen, Jayaram Raghuram, Jihye Choi +3
Recently, there is an emerging interest in adversarially training a classifier with a rejection option (also known as a selective classifier) for boosting adversarial robustness. W…
Rethinking Diversity in Deep Neural Network Testing
Zi Wang, Jihye Choi, Ke Wang +1
Motivated by the success of traditional software testing, numerous diversity measures have been proposed for testing deep neural networks (DNNs). In this study, we propose a shift…
Concept-Based Explanations for Tabular Data
Varsha Pendyala, Jihye Choi
The interpretability of machine learning models has been an essential area of research for the safe deployment of machine learning systems. One particular approach is to attribute…
Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
Ryan Feng, Neal Mangaokar, Jihye Choi +2
Patch attacks against object detectors have been of recent interest due to their being physically realizable and more closely aligned with practical systems. In response to this th…
Concept-based Explanations for Out-Of-Distribution Detectors
Jihye Choi, Jayaram Raghuram, Ryan Feng +3
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improvi…
Stochastic Doubly Robust Gradient
Kanghoon Lee, Jihye Choi, Moonsu Cha +2
When training a machine learning model with observational data, it is often encountered that some values are systemically missing. Learning from the incomplete data in which the mi…