High Tech, High Touch



  • home
  • Research
  • Labs



Search article
  • Computer Systems & Intelligence (CSI) Lab - Prof. IKJUN YEOM

    Major research interests

    Wired/Wireless Computer Network

    Network performance evaluation

    Data Center networking including GPU direct networking

    NVMe-oF over TCP

    High speed networking for distributed machine learning

    Major research achievements (2021~present)

    "i-NVMe: Isolated NVMe over TCP for a Containerized Environment”, accepted to present at IEEE Infocom 2023.

    ““Virtualizing GPU direct packet I/O on commodity Ethernet to accelerate GPU-NFV,” Journal of Network and Computer Applications, 2022.

    “GPU-Ether: GPU-native packet I/O for GPU applications on commodity ethernet,” IEEE Infocom 2021.

    “Efficient user-level multi-path utilization in RDMA networks,” IEEE Access, 2021.

    “Gemma: reinforcement learning-based graph embedding and mapping for virtual network applications,” IEEE Access, 2021.

    “Repot: transferable reinforcement learning for quality-centric networked monitoring in various environments,” IEEE Access, 2021

    NVME over TCP optimization with FPGA project supported by Samsung Electronics, 2022-2024.

    GPU Direct Communication over Commodity Ethernet project supported by NRF Korea, 2021-2023.

  • Software Security Lab - Prof. SUNGJAE HWANG

    Major research interests

    Software Security

    System Security (Android, Blockchain, Automotive)

    Software Testing & Program Analysis

    Empirical Security

    Major research achievements (2020~present)

    “JUSTGen: Effective Test Generation for Unspecified JNI Behaviors on JVMs”, Sungjae Hwang, Sungho Lee, Jihoon Kim, and Sukyoung Ryu, 43rd ACM/IEEE International Conference on Software Engineering (ICSE), 2021

    “Gap between Theory and Practice: An Empirical Study of Security Patches in Solidity”, Sungjae Hwang, and Sukyoung Ryu42nd ACM/IEEE International Conference on Software Engineering (ICSE), 2022

    “All about Activity Injection: Threats, Semantics, Detection, and Defense”, Sungjae Hwang, Sungho Lee, and Sukyoung Ryu, Software Practice and Experience (SPE), 2020

    Major research Projects (2021~present)

    AI Platform to Fully Adapt and Reflect Privacy-Policy Changes.

    (Funded by Institute for Information & Communication Technology Planning & Evaluation)

    A Metric to Measure the Quality of Decompiled Codes. (Funded by National Security Research)

    IoT Firmware Re-Hosting for Security Analysis. (Funded by National Security Research)

    Static Analysis Framework for Automotive Software. (Funded by National Research Foundation of Korea)

    Security Testing Framework for Misuse of Web API. (Funded by National Security Research)

  • Visual Computing Lab - Prof. JAE-PIL HEO

    Major research interests

    Image/video classification and object detection

    Robust models to data scarcity, long-tailed distribution, and open-set

    Semantic segmentation

    Unsupervised, semi-supervised, and weakly-supervised techniques

    Image/video retrieval

    Scalable algorithms for large-scale high-dimensional search, moment retrieval

    Generative models for images and videos

    GANs and denoising diffusion probabilistic models

    Representation learning for visual data

    Self-supervised, unsupervised representation learning

    Image/video super-resolution

    Very small image super-resolution, spatio-temporal video super-resolution

    Major research achievements (2021 — present)

    Disentangled Representation Learning for Unsupervised Neural Quantization, CVPR 2023

    Query-Dependent Video Representation for Moment Retrieval and Highlight Detection, CVPR 2023

    Leveraging Hidden Positives for Unsupervised Semantic Segmentation, CVPR 2023

    Progressive Few-shot Adaption of Generative Model with Align-free Spatial Correlation, AAAI 2023

    Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition, AAAI 2023

    Tailoring Self-Supervision for Supervised Learning, ECCV 2022

    Difficulty-Aware Simulator for Open Set Recognition, ECCV 2022

    Local Attention Pyramid for Scene Image Generation, CVPR 2022

    Task Discrepancy Maximization for Fine-grained Few-Shot Classification, CVPR 2022

    Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search, ICCV 2021

    Collaborative Learning with Disentangled Features for Zero-shot Domain Adaptation, ICCV 2021

    Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency, CVPR 2021

  • Computer Systems & Intelligence (CSI) Lab - Prof. HWANSOO HAN

    Research Interests

    Deep Learning Compiler

    Compiler Optimizations for HW Accelerators (GPU/FPGA)

    System SW for Non-Volatile Memory

    Current Research Grants

    High-Performance Exabyte Storage Systems (HiPer), Samsung Electronics, 2022.7-2024.6

    Improving FPGA Programmability for Big Data Analytics, NRF, 2021.3-2025.2

    Research on Edge Native Operating Systems for Edge Micro-Data-Centers, IITP, 2021.1-2024.12

    Selected Publications (2021-present)

    Accelerating Deep Neural Networks on Mobile Multicore NPUs, ACM/IEEE International Symposium on Code Generation and Optimization (CGO), Feb 2023.

    Libpubl: Exploiting Persistent User Buffers as Logs for Write Atomicity, ACM Workshop on Hot Topics in Storage and File Systems (HotStorage), Jul 2021.

    Idempotence-Based Preemptive GPU Kernel Scheduling for Embedded Systems, IEEE Transactions on Computers (IEEE TC), Vol. 70(3), pp. 332-346, Mar 2021.

  • Data Science and Artificial Intelligence Lab (DSAIL) - Prof. JINYOUNG HAN

    Major research interests

    Multimodal Learning, Human-centered ML, Human-AI Interaction

    Social Computing, Mental Health, Digital Therapeutics, Human-like Chatbot

    Medical computing, Healthcare, Clinical Decision Support System (CDSS)

    X-Analytics or X-Computing (X = Business, Culture, Politics, Sports, Game, Law, etc.)

    Major research achievements (2021~present)

    "AlphaDAPR: An AI-based Explainable Expert Support System for Art Therapy," ACM Conference on Intelligent User Interfaces (IUI), Mar. 2023.

    "Experiencing stress during COVID-19: A computational analysis of stressors and emotional responses to stress," Cyberpsychology, Behavior, and Social Networking, Vol. 25, Issue 9, pp. 561-570, Sep. 2022. (SSCI, JCR 2021 IF = 6.135)

    "Magic Brush: An AI-based Service for Dementia Prevention focused on Intrinsic Motivation," ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW), Nov. 2022.

    "Predicting Emotional Intensity in Political Debates via Non-verbal Signals," INTERSPEECH, Sep. 2022.

    "Why Tag Me?: Detecting Motivations of Comment Tagging in Instagram," Expert Systems With Applications, vol. 202, pp.117171, Sep. 2022. (SCIE, JCR 2021 IF=8.665)

    "Detecting Suicidality with a Contextual Graph Neural Network," The workshop on Computational Linguistics and Clinical Psychology (CLPsych), Jul. 2022.

    "Preventing Rumor Spread with Deep Learning," Expert Systems With Applications, vol. 197, pp. 116688, Jul. 2022. (SCIE, JCR 2021 IF=8.665)

    "D-Vlog: Multimodal Vlog Dataset for Depression Detection," AAAI Conference on Artificial Intelligence (AAAI), Feb. 2022.

    "Evaluating Audience Loyalty and Authenticity in Influencer Marketing via Multi-task Multi-relational Learning," International AAAI Conference on Web and Social Media (ICWSM), Jun. 2021.

    "Distinguishing Retinal Angiomatous Proliferation from Polypoidal Choroidal Vasculopathy with A Deep Neural Network based on Optical Coherence Tomography," Scientific Reports 11, 9275(2021), Apr. 2021. (SCI, JCR 2021 IF = 4.996)

  • Superintelligence Lab - Prof. HYUNSEUNG CHOO

    Major research interests

    Data Deep Learning (Life log, Network, Facial, Baseball)

    Medical Image Processing (Eye Fundus, Bone and Chest X-Ray)

    Intelligent Internet of Things (IoT), Human “Things” Interactions (Robot, Drone, Energy)

    “Autonomous” Ad hoc and Sensor Networks, Network Softwarization (Netsoft-SDN/NFV)

    Major projects

    Ministry of Science and ICT, Korea, ICT Creative Consilience Program (USD 30M/10 years)

    Ministry of Science and ICT, Korea, Grand ICT (USD 20M/8 years)

    Ministry of Education, Korea, Convergence Research Institute (USD 4.2M/9 years)

    Ministry of ICT, Korea, HCI Convergence Research Center (USD 5.3M/8 years)

    (Total Amount of Research Fund Granted: USD 80M)

    Major research achievements (2021~present)

    "Monotone Split and Conquer for Anomaly Detection in IoT Sensory Data," IEEE Internet of Things Journal, Vol. 8, pp. 15468-15485, 2021 (IF 10.24)

    "Sensory Data Aggregation in Internet of Things: Period-driven Pipeline Scheduling Approach," IEEE Transaction on Mobile Computing, Vol. 21, pp. 3326-3341, 2021 (IF 6.08)

    "Link-delay-aware Reinforcement Scheduling for Data Aggregation in massive IoT,"  IEEE Transactions on Communications, Vol. 70, pp. 5353-5367, 2022 (IF 6.17)

    "Improved GAN with Fact Forcing for Mobility Prediction," Elsevier Journal of Network and Computer Applications, Vol 207, 103488, 2022 (IF 9.29)

    "iPaaS: Intelligent Paging as a Service," IEEE Networks, Early Access, 2022 (IF 11.29)

    "Deep Mobile Path Prediction with Shift-and-Join and Carry-Ahead," IEEE Transactions on Cognitive Communications and Networking, 2023 (IF 6.36)

  • Hackers In inTrusion Lab - Prof. HYOUNG-KEE CHOI

    Major Research Interests

    Wireless network security

    - IEEE 802.11i (known as Wi-Fi)/ WPA version 3

    - 5G mobile network/ Distributed mobility management (DMM)

    - Internet of Things (IoT)/ M2M, MTC

    vulnerability assessments to systems.

    Major Research Achievements (2017~present)

    Kwon, S., & Choi, H.-K. (2022). Study on Message Exposure to Administrator in Secure Messaging Protocol MLS. Journal of the Korea Institute of Information Security & Cryptology

    Security Analysis and Bypass User Authentication Bound to Device of Windows Hello in the Wild E Kim, HK Choi - Security and Communication Networks, 2021

    Evolution of Wi-Fi protected access: security challenges

    S Kwon, HK Choi - IEEE Consumer Electronics Magazine, 2020

    Secure and efficient binding updates in host-based distributed mobility management

    S Lee, HK Choi, E Kim, JH Lee - Wireless Networks, 2019

    Mutual authentication method and system with network in machine type communication

    HK Choi, DS Choi, YJ Kim, JY Park, DH Shin, JW Yu - US Patent 9,866,554, 2018

    Privacy-preserving nearest neighbor queries using geographical features of cellular networks

    MD Firoozjaei, J Yu, H Choi, H Kim - Computer Communications, 2017

    Secure and efficient binding updates in host-based distributed mobility management

    S Lee, HK Choi, EJ Kim - Journal of the Korea Institute of Information Security & …, 2017

  • Software Analysis Lab - Prof. SOOYOUNG CHA

    Major Research Interests

    My research aims to develop software analysis techniques for safe and reliable software.

    AI-based software testing for automatically detecting software bugs

    Machine-learning-guided static analysis

    Major Research Achievements (2021~present)

    "Learning Seed-Adaptive Mutation Strategies for Greybox Fuzzing”, International Conference on Software Engineering (ICSE), 2023.

    "Enhancing Dynamic Symbolic Execution by Automatically Learning Search Heuristics”, IEEE Transactions on Software Engineering (TSE), Volume 48, No. 9, Pages 3640-3663. 2022.

    "SymTuner: Maximizing the Power of Symbolic Execution by Adaptively Tuning External Parameters”, International Conference on Software Engineering (ICSE), 2022.

    Awards (2021~present)

    ACM SIGSOFT Distinguished Paper Award at International Conference on Software Engineering (ICSE), 2022.

  • Computing Platforms Lab - Prof. HYUNGMIN CHO

    Major research interests

    Computing Platforms for Machine Learning

    Accelerator Architectures

    Processor Reliability and Verification  

    Major research achievements (2021~present)

    “ES4D: Accelerating Exact Similarity Search for High-Dimensional Vectors via Vector Slicing and In-SSD Computation” – Juhwan Kim, Jongseon Seo, Jonghyeok Park, Sangwon Lee, Hongchan Roh and Hyungmin Cho, International Conference on Computer Design (ICCD), 2022

    “Know Your Neighbor: Physically Locating Xeon Processor Cores on the Core Tile Grid” – Hyungmin Cho, Design, Automation & Test in Europe Conference & Exhibition (DATE) 2022

    “FARNN: FPGA-GPU Hybrid Acceleration Platform for Recurrent Neural Networks” – Hyungmin Cho, Jeesoo Lee, Jaejin Lee, IEEE TPDS 2021

    “SpecMCTS: Accelerating Monte Carlo Tree Search Using Speculative Tree Traversal” – Juhwan Kim, Byeongmin Kang, Hyungmin Cho, IEEE Acess 2021

    “RiSA: A Reinforced Systolic Array for Depthwise Convolutions and Embedded Tensor Reshaping” – Hyungmin Cho, ACM TECS 2021

    “Minimal Aliasing Single-Error-Correction Codes for DRAM Reliability Improvement” – Sung-Il Pae, Vivek Kozhikkottu, Dinesh Somasekar, Wei Wu, Shankar Ganesh Ramasubramanian, Melin Dadual, Hyungmin Cho, Kon-Woo Kwon, IEEE ACCESS 2021

  • Interactive Data Computing Lab - Prof. JAEMIN JO

    Major research interests

    Human-Data(AI) Interaction

    Information Visualization

    Progressive Visual Analytics

    Automated Data Analysis

    Major research achievements (2021~present)

    “RCMVis: A Visual Analytics System for Route Choice Modeling”, IEEE Transactions on Visualization and Computer Graphics (TVCG), Mar.2023

    “Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works”, ACM Annual Conference on Intelligent User Interfaces (IUI), Mar.2023

    “We-toon: A Communication Support System between Writers and Artists in Collaborative Webtoon Sketch Revision”, ACM Symposium on User Interface Software and Technology (UIST), Oct.2022

    “SizePairs: Achieving Stable and Balanced Temporal Treemaps using Hierarchical Size-based Pairing”, IEEE VIS (VIS), Oct.2022

    “Uniform Manifold Approximation with Two-phase Optimization”, IEEE VIS Short (VIS), Oct.2022

    “Intentable: A Mixed-Initiative System for Intent-Based Chart Captioning” , IEEE VIS Short (VIS), Oct.2022

    “Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets”, IEEE VIS (VIS), Oct.2021

    “Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections” , IEEE VIS (VIS), Oct.2021

    “ProReveal: Progressive Visual Analytics with Safeguards”, Transactions on Visualization and Computer Graphics (TVCG), Jul.2021

    “Comparative Layouts Revisited: Design Space, Guidelines, and Future Directions” , IEEE Transactions on Visualization and Computer Graphics (TVCG), Mar.2021.