Insik Shin

Insik Shin

Auto-generated profile, based on publicly available information

Insik Shin

KAIST, Daejeon, Republic of Korea

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 July 2009 in Real-Time Systems
Verified
Journal Article
Closed access
PDF file
AEArvind Easwaran
Arvind Easwaran
ISInsik Shin
Insik Shin
ILInsup Lee
Insup Lee

28 February 2018 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
SKSi-Hyuck Kang
Si-Hyuck Kang
BJByunggill Joe
Byunggill Joe
YYYeonyee Yoon
Yeonyee Yoon
GCGoo-Yeong Cho
Goo-Yeong Cho
ISInsik Shin
Insik Shin
JSJung-Won Suh
Jung-Won Suh
Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.

4 December 2024
Verified
Conference Paper
Open access
SLSunjae Lee
Sunjae Lee
JCJunyoung Choi
Junyoung Choi
JLJungjae Lee
Jungjae Lee
MWMunim Hasan Wasi
Munim Hasan Wasi
HCHojun Choi
Hojun Choi
ISInsik Shin
Insik Shin
The advent of large language models (LLMs) has opened up new opportunities in the field of mobile task automation. Their superior language understanding and reasoning capabilities allow users to automate complex and repetitive tasks. However, due to the inherent unreliability and high operational cost of LLMs, their practical applicability is quite limited. To address these issues, this paper introduces MobileGPT1, an innovative LLM-based mobile task automator equipped with a human-like app memory. MobileGPT emulates the cognitive process of humans interacting with a mobile app---explore, select, derive, and recall. This approach allows for a more precise and efficient learning of a task's procedure by breaking it down into smaller, modular sub-tasks that can be re-used, re-arranged, and adapted for various objectives. We implement MobileGPT using online LLMs services (GPT-3.5 and GPT-4) and evaluate its performance on a dataset of 185 tasks across 18 mobile apps. The results indicate that MobileGPT can automate and learn new tasks with 82.7% accuracy, and is able to adapt them to different contexts with near perfect (98.75%) accuracy while reducing both latency and cost by 62.5% and 68.8%, respectively, compared to the GPT-4 powered baseline.

19 August 2022 in JMIR Medical Informatics
Verified
Journal Article
Open access
BJByunggill Joe
Byunggill Joe
YPYonghyeon Park
Yonghyeon Park
JHJihun Hamm
Jihun Hamm
ISInsik Shin
Insik Shin
JLJiyeon Lee
Jiyeon Lee
Background: A backdoor attack controls the output of a machine learning model in 2 stages. First, the attacker poisons the training data set, introducing a back door into the victim’s trained model. Second, during test time, the attacker adds an imperceptible pattern called a trigger to the input values, which forces the victim’s model to output the attacker’s intended values instead of true predictions or decisions. While backdoor attacks pose a serious threat to the reliability of machine learning–based medical diagnostics, existing backdoor attacks that directly change the input values are detectable relatively easily. Objective: The goal of this study was to propose and study a robust backdoor attack on mortality-prediction machine learning models that use electronic health records. We showed that our backdoor attack grants attackers full control over classification outcomes for safety-critical tasks such as mortality prediction, highlighting the importance of undertaking safe artificial intelligence research in the medical field. Methods: We present a trigger generation method based on missing patterns in electronic health record data. Compared to existing approaches, which introduce noise into the medical record, the proposed backdoor attack makes it simple to construct backdoor triggers without prior knowledge. To effectively avoid detection by manual inspectors, we employ variational autoencoders to learn the missing patterns in normal electronic health record data and produce trigger data that appears similar to this data. Results: We experimented with the proposed backdoor attack on 4 machine learning models (linear regression, multilayer perceptron, long short-term memory, and gated recurrent units) that predict in-hospital mortality using a public electronic health record data set. The results showed that the proposed technique achieved a significant drop in the victim’s discrimination performance (reducing the area under the precision-recall curve by at most 0.45), with a low poisoning rate (2%) in the training data set. In addition, the impact of the attack on general classification performance was negligible (it reduced the area under the precision-recall curve by an average of 0.01025), which makes it difficult to detect the presence of poison. Conclusions: To the best of our knowledge, this is the first study to propose a backdoor attack that uses missing information from tabular data as a trigger. Through extensive experiments, we demonstrated that our backdoor attack can inflict severe damage on medical machine learning classifiers in practice.

19 April 2023
Verified
Conference Paper
Open access
SSSeoyun Son
Seoyun Son
JCJunyoug Choi
Junyoug Choi
SLSunjae Lee
Sunjae Lee
JSJean Y Song
Jean Y Song
ISInsik Shin
Insik Shin
Online meetings are indispensable in collaborative remote work environments, but they are vulnerable to distractions due to their distributed and location-agnostic nature. While distraction often leads to a decrease in online meeting quality due to loss of engagement and context, natural multitasking has positive tradeoff effects, such as increased productivity within a given time unit. In this study, we investigate the impact of real-time transcriptions (i.e., full-transcripts, summaries, and keywords) as a solution to help facilitate online meetings during distracting moments while still preserving multitasking behaviors. Through two rounds of controlled user studies, we qualitatively and quantitatively show that people can better catch up with the meeting flow and feel less interfered with when using real-time transcriptions. The benefits of real-time transcriptions were more pronounced after distracting activities. Furthermore, we reveal additional impacts of real-time transcriptions (e.g., supporting recalling contents) and suggest design implications for future online meeting platforms where these could be adaptively provided to users with different purposes.

25 February 2014 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
JLJinkyu Lee
Jinkyu Lee
KSKang G. Shin
Kang G. Shin
ISInsik Shin
Insik Shin
AEArvind Easwaran
Arvind Easwaran
With increasing popularity and deployment of multi-core chips in embedded systems, a number of real-time multiprocessor scheduling algorithms have been proposed along with their schedulability analyses (or tests), which verify temporal correctness under a specific algorithm. Each of these algorithms often comes with several different schedulability tests, especially when it is difficult to find exact schedulability tests for the algorithm. Such tests usually find different task sets deemed schedulable even under the same scheduling algorithm. While these different tests have been compared with each other in terms of schedulability performance, little has been done on how to combine such different tests to improve the overall schedulability of a given scheduling algorithm beyond a simple union of their individual schedulability. Motivated by this, we propose a composition theory for schedulability tests with two new methods. The first method composes task-level timing guarantees derived from different schedulability tests, and the second one derives system-level schedulability results from a single schedulability test. The unified composition theory with these two methods then utilizes existing schedulability tests effectively so as to cover additional schedulable task sets. The proposed composition theory is shown to be applicable to most existing preemptive/non-preemptive scheduling algorithms. We also present three case-studies, demonstrating how and by how much the theory can improve schedulability by composing existing schedulability tests. Our evaluation results also show that the composition theory makes it possible to cover up to 181.7 percent additional schedulable task sets for preemptive fpEDF, preemptive EDF and non-preemptive EDF scheduling algorithms beyond their existing tests.