주요연구관심분야

멀티모달학습

시각-언어 모델

도메인 전이

로봇 비전

계산 효율적인 전이 학습

주요연구실적 (2021ᅳ 현재)

“Intra-Inter Modal Attention Blocks for RGB-D Semantic Segmentation” Soyun Choi, Youjia Zhang, and Sungeun Hong Jun 2023, International Conference on Multimedia Retrieval (ICMR '23 Oral)

“TL-ADA: Transferable Loss-based Active Domain Adaptation” Kyeongtak Han, Youngeun Kim, Dongyoon Han, Hojun Lee, and Sungeun Hong Apr 2023, Neural Networks, Elsevier

“IFQA: Interpretable Face Quality Assessment” Byungho Jo, Donghyeon Cho, In Kyu Park, and Sungeun Hong Jan 2023, Winter Conference on Applications of Computer Vision (WACV '23)

“Spatio-channel Attention Blocks for Cross-modal Crowd Counting” Youjia Zhang, Soyun Choi, and Sungeun Hong Dec 2022, Asian Conference on Computer Vision (ACCV '22 Oral)

“Adaptive Graph Adversarial Networks for Partial Domain Adaptation” Youngeun Kim and Sungeun Hong Jan 2022, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

주요연구관심분야

Culture & Media Informatics

Innovation Studies

Digital Media Society

주요연구실적 (2021ᅳ현재)

(2023)  메타버스 사용자의 사회⋅심리적 특성이 아바타 커스터마이징에 미치는 영향.  사이버커뮤니케이션학보.  40,  2

(2023)  Changes in regional knowledge bases and its effect on local labour markets in the midst of transition: Evidence from France over 1985-2015.  APPLIED SPATIAL ANALYSIS AND POLICY.  16,  3

(2023)  The Return of the King: The Importance of Killer Content in a Competitive OTT Market.  JOURNAL OF THEORETICAL AND APPLIED ELECTRONIC COMMERCE RESEARCH.  18,  2

(2023)  The effect of watching OTT late at night on the sleep pattern of users.  SLEEP AND BIOLOGICAL RHYTHMS.  21,  4

(2023)  Regional knowledge spaces: the interplay of entry-relatedness and entry-potential for technological change and growth.  JOURNAL OF TECHNOLOGY TRANSFER.  48,  2

(2023)  The Optimal Open Innovation Strategy with Science-based Partners for Venture Firm's Innovation Capabilities: Focusing on Innovation Modes.  SCIENCE TECHNOLOGY AND SOCIETY.  28,  2

(2023)  The effects of popularity metrics in news comments on the formation of public opinion: Evidence from an internet portal site.  SOCIAL SCIENCE JOURNAL.  60,  2

(2023)  An Analysis of Factors Influencing the Intention to Use "Untact" Services by Service Type.  SUSTAINABILITY.  15,  4

(2023)  Which innovation type is better for production efficiency? A comparison between product/service, process, organisational and marketing innovations using stochastic frontier and meta-frontier analysis.  TECHNOLOGY ANALYSIS & STRATEGIC MANAGEMENT.  35,  1

주요연구관심분야

모바일/블록체인/자동차 보안

소프트웨어 테스팅

프로그램 분석

주요연구실적 (2019~현재)

JUSTGen (ICSE 2021): 가상머신 동작 검증을 위한 동적 테스팅 프레임워크 제안. JVM 의 792 개의 버그를 리포트 하였으며, 563 개의 버그가 수정됨.

Smart Contract Security (ICSE 2020): 스마트 컨트랙트 쥐약점 탐지 분석기 제안. 13,943개의 스마트 컨트랙트에서 보안 문제를 발견 및 리포트하여 CVE8 개 발급받음

Activity Injection (SPE 2020): 안드로이드 플랫폼에서 새로운 공격 방식을 개발하고 이를 자동으로 탐지하는 정적분석기 제안.

주요연구관심분야

소프트웨어 테스팅 (화이트-박스 테스팅)

데이터-기반 소프트웨어 취약점 자동 검출 기술

기계학습 기반 정적-분석 기술

주요연구실적 (2019~현재)

SymTuner (ICSE 2022): 화이트-박스 SW 테스팅 도구들의 외부 파라미터들을 기계-학습 기법을 이용해서 자동으로 조정해주는 기술.

ParaDySE (IEEE Transactions on Software Engineering 2022): 동적 기호실행의 핵심 기법인 탐색 전략《Search Heuristic)을 자동으로 생성하는 기술.

ADAPT (ISSTA 2020): 심층 신경망(Deep Neural Network)의 취약점을 효과적으로 검출하기 위한 화이트-박스 테스팅 기술.

HOMI (ESEC/FSE 2020): 각 프로그램에 최적화된 동적 기호실행의 '상태-자르기 전략(State-Pruning Heuristic)'을 자동으로 학습하는 기술.

Chameleon (ESEC/FSE 2019): 화이트-박스 테스팅 기법 "콘콜릭 테스팅 (Concolic Testing广의 코드 탐색 기준을 기계-학습을 통해 적응적으로(Adaptively) 바꿔주는 기술

주요연구관심분야

Cloud-Based Security Systems - Interface to Network Security Functions (I2NSF): https://datatracker.ietf.org/wg/i2nsf/documents/

Vehicular Networking - IPv6 Wireless Access in Vehicular Environments (IPWAVE):

https://datatracker.ietf.org/wg/ipwave/documents/

SNS Influencer Marketing Platform: https://ieeexplore.ieee.org/document/9728965

Indoor Positioning Systems: https://ieeexplore.ieee.org/document/9296763

주요연구실적 (2020~현재)

“Context-Aware Navigation Protocol for Safe Driving in Vehicular Cyber-Physical Systems”, IEEE Transactions on Intelligent Transportation Systems, CNP supplemental material, Vol. 24, No. 1, pp. 128-138, January 2023.

“A comprehensive survey on data dissemination in Vehicular Ad Hoc Networks”, Elsevier Vehicular Communications, Vol. 34, April 2022.

“A comprehensive survey on vehicular networking for safe and efficient driving in smart transportation: A focus on systems, protocols, and applications”, Elsevier Vehicular Communications, Vol. 31, October 2021.

“A comprehensive survey on vehicular networks for smart roads: A focus on IP-based approaches”, Elsevier Vehicular Communications, Vol. 29, June 2021.

“DFC: Device-Free Human Counting through Wi-Fi Fine-Grained Subcarrier Information”, IET Communications, Vol. 15, Issue 3, pp. 337–350, January 2021.

“Particle Filtering-Based Indoor Positioning System for Beacon Tag Tracking”, IEEE Access, December 2020.

“IBCS: Intent-Based Cloud Services for Security Applications”, IEEE Communications Magazine, Vol. 58, No. 4, pp. 45-51, April 2020.

“DAPF: Delay-Aware Packet Forwarding for Driving Safety and Efficiency in Vehicular Networks”, IET Communications, January 2020.

주요연구관심분야

Story Comprehension and Generation

Natural Language Processing

Text Analysis, Data Mining

주요연구실적 (2019~현재)

Genre-Controllable Story Generation via Supervised Contrastive Learning. The ACM Web Conference 2022

Analysis of Autoencoders for Network Intrusion Detection. Sensors. 2021

Extracting and Clustering of Story Events from a Story Corpus. KSII Transactions on Internet & Information Systems 2021

The CreativeSumm 2022 Shared Task: A Two-Stage Summarization Model using Scene Attributes. The Workshop on Automatic Summarization for Creative Writing (ACL) 2022

A Fast and Efficient Stochastic Opposition-Based Learning for Differential Evolution in Numerical Optimization, Swarm and Evolutionary Computation. 2021

Advanced Cauchy Mutation for Differential Evolution in Numerical Optimization. IEEE Access. 2020

연구과제

Basic Science Research Program (2019-2023, NRF): Research on Text Understanding Techniques for Intelligent Story Generation Systems

ETRI (’20-’23, Ministry of Science and ICT - IITP) – Development of 5G Edge Security Technology for Ensuring 5G+ Service Stability and Availability

NCSoft (‘21-’22) - Analysis of Story Structure

SKKU Convergence Research Fund (’20, Collaboration with Samsung Hospital) - Development of an Ophthalmologist Chatbot

ICT Information Technology Research Center Support Program (’17-’22, Ministry of Science and ICT - IITP) - Content Creation Technology Utilizing Artificial Intelligence

주요연구관심분야

Operating Systems

Cloud Computing

Storage System

Embedded Computing

주요연구실적

Transparently Exploiting Device-reserved Memory for Application Performance in Mobile Systems, IEEE Transactions on Mobile Computing, vol. 15, no. 11, pp. 2878-2891, Nov 2016, Jinkyu Jeong, Hwanju Kim, and Joonwon Lee

Cache Scheme of Shared-Buffer Mappings for Energy-Efficiency of Mobile Devices, IET Electronics Letters, vol. 51, no. 11, pp. 830-832, May 2015, Jinkyu Jeong, Joonwon Lee and Euiseong Seo

Exploiting Asymmetric CPU Performance for Fast Startup of Subsystem in Mobile Smart Devices, IEEE Transactions on Consumer Electronics, vol. 61, no. 1, pp. 103-111, Feb. 2015, Jun Kim, Joonwon Lee, and Jinkyu Jeong

Virtual Asymmetric Multiprocessor for Interactive Performance of Consolidated Desktops, ACM SIGPLAN Notices, vol. 49, no. 7, pp. 29-40, Jul. 2014, Hwanju Kim, Sangwook Kim, Jinkyu Jeong, and Joonwon Lee.

Sung-hun Kim, Jinkyu Jeong, and Joonwon Lee, "Selective Memory Deduplication for Cost Efficiency in Mobile Smart Devices," IEEE Transactions on Consumer Electronics, Vol. 60, Issue 2, pp. 276-284, May 2014

Group-based Memory Oversubscription for Virtualized Clouds, Journal of Parallel and Distributed Computing, Vol. 74, Issue 4, pp. 2241-2256, April 2014, Sangwook Kim, Hwanju Kim, Joonwon Lee and Jinkyu Jeong

Analysis of Virtual Machine Live-Migration as a Method for Power-Capping, Journal of Supercomputing, Vol. 66, Issue 3, pp. 1629-1655, December 2013, Jinkyu Jeong, Sung-hun Kim, Hwanju Kim, Joonwon Lee, Euiseong Seo

Efficient Function Call Tracing with Link-Time Binary Rewriting for CE Devices, IEEE Transactions on Consumer Electronics, Vol. 59, Issue 4, pp. 892-900, November 2013, Bon-Keun Seo, Jinkyu Jeong, Joonwon Lee, and Euiseong Seo

Demand-Based Coordinated Scheduling for SMP VMs, ASPLOS 2013

주요연구관심분야

Pattern Recognition, Machine Learning, Computer Vision, Big Data Analytics

Multimedia, loT/loMTr Image and Video Processing, Information Security, Fire/Smoke Scene Analysis

주요연구실적 (2016-현재)

Invited Speaker for topic "F니ture of E-Health and Telemedicine" under the program "MARIE CURIE COFUND PROGRAMME/； scheduled on 21st April 2021.

Invited Speech on "Intelligent Video Summary Generation: Current Challenges and Future Directions" at 2020 International Conference on Intelligent Data Science Technologies and Applications (IDSTA), Valencia, Spain.

Invited Speech on 'Intelligent Video Summary Generation: Current Challenges and Future Di recti onsH at The Fourth International Conference on Multimedia Computing, Networking and Applications (MCNA2020), Valencia, Spain.

주요연구관심분야

Security engineering

Usable security

주요연구실적 (2021~현재)

“SmartMark: Software Watermarking Scheme for Smart Contracts”, Taeyoung Kim, Yunhee Jang, Chanjong Lee, Hyungjoon Koo, and Hyoungshick Kim, ICSE: The 45th International Conference on Software Engineering, Melbourne, Australia, 2023.

“AppSniffer: Towards Robust Mobile App Fingerprinting Against VPN”, Sanghak Oh, Minwook Lee, Hyunwoo Lee, Elisa Bertino, and Hyoungshick Kim, WWW: The 32nd Web Conference, Austin, USA, 2023.

“Mutexion: Mutually Exclusive Compression System for Mitigating Compression Side-Channel Attacks”, Taegeun Moon, Hyoungshick Kim, and Sangwon Hyun, ACM Transactions on the Web (TWEB), 2022.

“Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things”, Yansong Gao, Minki Kim, Chandra Thapa, Alsharif Abuadbba, Zhi Zhang, Seyit Camtepe, Hyoungshick Kim, and Surya Nepal, IEEE Transactions on Computers (TC), 2022.

“Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks”, Yansong Gao, Yeonjae Kim, Bao Gia Doan, Zhi Zhang, Gongxuan Zhang, Surya Nepal, Damith C. Ranasinghe, and Hyoungshick Kim, IEEE Transactions on Dependable and Secure Computing (TDSC), 2022.

“ARGH!: Automated Rumor Generation Hub”, Larry Huynh, Manh Duy Thai Nguyen, Joshua Goh, Hyoungshick Kim, and Jin Hong, CIKM: The 30th ACM International Conference on Information and Knowledge Management (selected as “best paper nominations”), Virtual, 2021.

“Rocky: Replicating Block Devices for Tamper and Failure Resistant Edge-based Virtualized Desktop Infrastructure”, Beom Heyn Kim and Hyoungshick Kim, ACSAC: The 37th Annual Computer Security Applications Conference, Virtual, 2021.

“Fine with “1234”? An Analysis of SMS One-Time Password Randomness in Android Apps”, Siqi Ma, Juanru Li, Hyoungshick Kim, Elisa Bertino, Surya Nepal, Diet Ostry, and Cong Sun, ICSE: The 43rd International Conference on Software Engineering, Madrid, Spain, 2021

주요연구관심분야

GPU 활용 네트워킹 및 그 응용 어플리케이션

향상된 컨테이너 자원 관리 기법 （간섭, 네트워킹）

기계 학습 성능 향상을 위한 GPU 자원 관리 기법 연구

주요연구실적 （2019~현재）

GPU-Ether （Infocom 2021）: GPU 어플리케이션을 위한 GPU-NIC 직접 통신 기법에 관한 연구. 10Gbps 기준 모든 패킷 사이즈에 대해 성능 저하 없이 GPU 로 패킷 전송이 가능하며 지연시간, 쓰루풋 기준 최대 80%의 성능 향상을 보임,