Core AI | 서울대학교AI연구원(AIIS)

팝업레이어 알림

팝업레이어 알림이 없습니다.

RESEARCH

Core AI

AIIS (Artificial Intelligence Institute at Seoul National University) is an intercollegiate research institute
committed to integrating and supporting AI-related research. As a hub of AI research both in Core AI
and X+AI areas, researchers of diverse disciplines collaborate through AIIS.

AI Security

AIIS works on both parts of AI security – adopting AI technology to develop safer computer systems
and building a defense system against AI-based computer attacks.

Kwon, Taekyoung Department of Computer Science and Engineering

  • Research Lab Network Convergence & Security Laboratory
  • Research Area (Core AI)Vision & Perception, Data Intelligence, AI Security
  • Research Area (X+AI)Humanities/Social Sciences, Commerce

대표논문

"Magnetic Field based Indoor Localization System: A Crowdsourcing Approach",  International Conference on Indoor Positioning and Indoor Navigation (IPIN 2019), Pisa, Italy, September 2019
"Unveiling a Socio-Economic System in a Virtual World: A Case Study of an MMORPG", World Wide Web Conference (WWW) 2018 (Industry track), Lyon, France, April. 2018.
"Privacy Leakage in Event-based Social Networks: A Meetup Case Study", In Proceedings of ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW`18), Jersey City, United States, November 2018

Song, Hyun Oh Department of Computer Science and Engineering

  • Research Lab Machine Learning Lab
  • Research Area (Core AI)Learning & Reasoning, Robotics & Action, AI Security
  • Research Area (X+AI)Medicine, Finance

대표논문

Learning Discrete and Continuous Factors of Data via Alternating Disentanglement (ICML19)
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization (ICML19)
EMI: Exploration with Mutual Information (ICML19)
End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization (CVPR19)
[뉴럴 프로세싱 시스템 연구/16세부]Deep adversarial reinforcement learning via expert video demonstrations, 삼성전자(주)/민간지원사업, 2017-2020
머신러닝 기반 Storage 품질 예측 시스템의 향상을 위한 최적화기반 data augmentation 방법에 관한 연구, 삼성전자(주)/민간지원사업, 2019-2024
데이터간 범용적인 상호 유사성 추론을 위한 딥러닝 모형 연구, 과학기술정보통신부/이공분야기초연구사업전략공모사업, 2017-2020

Yoon, Sungroh Department of Electrical and Computer Engineering

  • Research Lab Data Science and AI Lab (DSAIL)
  • Research Area (Core AI)Learning & Reasoning, Vision & Perception, Language & Cognition, AI Platform, AI Chip, Data Intelligence, AI Security
  • Research Area (X+AI)Bio, Medicine, Pharma, Finance, Manufacturing, Energy

대표논문

Park, Soonae Department of Public Administration

  • Research Lab Public Management, Organizational Behavior, Environmental Administration, Policy Evaluation
  • Research Area (Core AI)Human-AI Interaction, Data Intelligence, AI Security
  • Research Area (X+AI)Humanities/Social Sciences, Finance, Energy

대표논문

Public Choice in Transit Organization and Finance: The Structure of Support. Transportation Research Record (SCI) 1669:87-95.
Regional Model of EKC for Air Pollution: Evidence from the Republic of Korea. Energy Policy (SSCI). 39, 2011
The Environmental Effects of the CNG Bus Program on Metropolitan Air Quality in Korea, The Annals of Regional Science (SSCI). 49 (1) 2012
Imperfect Information and Labor Market Bias against Small and Medium-sized Enterprises: A Korean Case, Small Business Economics: An Entrepreneurship Journal (SSCI). 2014. 10
Public Management in Korea: Performance Evaluation and Public Institutions (Ed). Routledge, 2018

Hur, Chung-Kil Department of Computer Science and Engineering

  • Research Lab Software Foundations Lab
  • Research Area (Core AI)AI Platform, AI Security
  • Research Area (X+AI)Medicine

대표논문

Paek, Yunheung Department of Electrical and Computer Engineering

  • Research Lab Security Optimization Research Lab.
  • Research Area (Core AI)AI Chip, AI Security
  • Research Area (X+AI)Finance, Commerce

대표논문

Hawkware: Network Intrusion Detection based on Behavior Analysis with ANNs on an IoT Device, Design Automation Conference (DAC), Jul 2020
DADE: a fast data anomaly detection engine for kernel integrity monitoring, The Journal of Supercomputing, Aug 2019
Real-Time Anomalous Branch Behavior Detection with a GPU-inspired Engine for Machine Learning Models, Design Automation and Test in Europe (DATE), Mar 2019
An SoC Architecture for Learning-Based Online Anomaly Detection on ARM, Design Automation Conference (DAC) WIP, Jun 2018
Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models, DEEP LEARNING AND SECURITY WORKSHOP, May 2018
Behavior-based Malware Detection in HW support, 1억, 삼성전자
AI 포렌식 빅데이터 기반 지능형 보안 위협 분석, 8500만, 서울특별시
Embedded 시스템에서의 (AI 기반) 공격탐지 및 데이터 전송 솔루션, 1억, 삼성전자

Yi, Kwangkeun Department of Computer Science and Engineering

  • Research Lab Programming Research Laboratory
  • Research Area (Core AI)AI Platform, AI Security, ai verification, security, safety
  • Research Area (X+AI)

대표논문

[book] Introduction to Static Analysis: an abstract interpretation perspective, MIT Press, 2020
Adaptive Static Analysis via Learning with Bayesian Optimization, TOPLAS 40(4), no.14, 2018
Global Sparse Analysis Framework, TOPLAS 36(3), no.8, 2014
Optimizing Homomorphic Evaluation Circuits by Program Synthesis and Term Rewriting, PLDI 2020
Selective Context-Sensitivity Guided by Impact Pre-Analysis, PLDI 2014
과기부 연구재단 선도연구센터(ERC), 소프트웨어무결점 연구센터, 센터장, 2008-2015
과기부 연구재단 창의연구단(CRI), 프로그램분석시스템 연구단, 연구단장, 1998-2003

Lee, Jaewook Department of Industrial Engineering

  • Research Lab Statistical Learning & Computational Finance Laboratory
  • Research Area (Core AI)Learning & Reasoning, AI Security
  • Research Area (X+AI)Finance

대표논문

Cheon, Jung Hee Department of Mathematical Sciences

  • Research Lab Homomorphic Encryption
  • Research Area (Core AI)AI Security, AI Theory
  • Research Area (X+AI)Medicine, Finance, Commerce

대표논문

Numerical Method for Comparison on Homomorphically Encrypted Numbers, With Dongwoo Kim, Duhyeong Kim, Hunhee Lee and Keewoo Lee, Asiacrypt'19 (Invited to Journal of Cryptology)
Statistical Zeroizing Attack: Cryptanalysis of Candidates of BP Obfuscation over GGH15 Multilinear Map, With Wonhee Cho, Minki Hhan, Jiseung Kim and Changmin Lee, CRYPTO'19
Cryptanalyses of Branching Program Obfuscations over GGH13 Multilinear Map from the NTRU Problem, With Minki Hhan, Jiseung Kim and Changmin Lee, CRYPTO'18