-
- 부교수
- 우사이먼성일
- 2022 SKKU Fellowship
-
- swoo@g.skku.edu
- N센터 4층 86407호실
-
관심분야
이상징후탐지, 데이터 마이닝/기계학습 응용, 보안, 프라이버시, 인간과컴퓨터상호작용, 인공위성시스템, 융합
학력
- Ph.D. Computer Science, 2017 University of Southern California (USC), Los Angeles, CA
약력/경력
- 연구원, 미국 항공우주국 제트추진연구소 (NASA-JPL)
학술지 논문
- (2025) Toward a robust approach to multivariate time series anomaly detection. JOURNAL OF MICRO-NANOPATTERNING MATERIALS AND METROLOGY-JM3. 24, 4
- (2025) Stealthy Query-Efficient Opaque Attack Against Interpretable Deep Learning. IEEE TRANSACTIONS ON RELIABILITY. 74, 3
- (2025) Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns. World Electric Vehicle Journal. 16, 1
- (2025) MIRACLE: Malware image recognition and classification by layered extraction. Data Mining and Knowledge Discovery. 39, 1
- (2024) Patch-wise vector quantization for unsupervised medical anomaly detection. PATTERN RECOGNITION LETTERS. 184,
- (2024) Hardening Interpretable Deep Learning Systems: Investigating Adversarial Threats and Defenses. IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING. 21, 4
- (2024) A real-world pharmacovigilance study on cardiovascular adverse events of tisagenlecleucel using machine learning approach. SCIENTIFIC REPORTS. 14, 1
- (2024) EAE-GAN: Emotion-Aware Emoji Generative Adversarial Network for Computational Modeling Diverse and Fine-Grained Human Emotions. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS. 11, 3
- (2024) Design and evaluation of highly accurate smart contract code vulnerability detection framework. DATA MINING AND KNOWLEDGE DISCOVERY. 38, 3
- (2023) Expectation-Maximization via Pretext-Invariant Representations. IEEE ACCESS. 11,
- (2023) Evaluating Trustworthiness and Racial Bias in Face Recognition APIs Using Deepfakes. COMPUTER. 56, 5
- (2023) Distance adaptive graph convolutional gated network-based smart air quality monitoring and health risk prediction in sensor-devoid urban areas. SUSTAINABLE CITIES AND SOCIETY. 91, 1
- (2023) DID We Miss Anything?: Towards Privacy-Preserving Decentralized ID Architecture. IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING. 20, 6
- (2023) An overhead-free region-based JPEG framework for task-driven image compression. PATTERN RECOGNITION LETTERS. 165, 1
- (2022) PasswordTensor: Analyzing and explaining password strength using tensor decomposition. COMPUTERS & SECURITY. 116,
- (2022) A Survey of Deep Learning-Based Object Detection Methods and Datasets for Overhead Imagery. IEEE ACCESS. 10, 1
- (2022) ORVAE: One-Class Residual Variational Autoencoder for Voice Activity Detection in Noisy Environment. NEURAL PROCESSING LETTERS. 54, 3
- (2021) Detecting handcrafted facial image manipulations and GAN-generated facial images using Shallow-FakeFaceNet. APPLIED SOFT COMPUTING. 105, 1
- (2021) Neural network laundering: Removing black-box backdoor watermarks from deep neural networks. COMPUTERS & SECURITY. 106,
- (2021) Will EU's GDPR Act as an Effective Enforcer to Gain Consent?. IEEE ACCESS. 9, 1
특허/프로그램
- 딥러닝 모델의 학습 데이터 삭제 방법 및 장치. 17-8817-53_____. 20241227. 대한민국
- 딥러닝과 자기조직화지도를 이용한 가상물리시스템에서의 이상치 탐지. 10-2022-0003261. 20231127. 대한민국
수상/공훈
- 국가보안연구소 원장상, 한국정보보호학회 동계학술대회 2018
- 장려상, 정보보호 데이터첼린지 2017
- 우수논문상, 한국정보보호학회 동계학술대회 2017
- 우수논문상, WISA 학회 2016
학술회의논문
- (2026) GAN or DM? In-depth Analysis and Evaluation of AI-generated Face Data for Generalizable Deepfake Detection. ACM SIGAPP Symposium on Applied Computing. 이탈리아
- (2025) RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator. Conference on Neural Information Processing Systems. 미국
- (2025) Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions. Conference on Neural Information Processing Systems. 미국
- (2025) Anomaly Detection for Advanced Driver Assistance System with NCDE-based Normalizing Flow. ACM Conference on Information and Knowledge Management. 대한민국
- (2025) Beyond Masking: Landmark-based Representation Learning and Knowledge-Distillation for Audio-Visual Deepfake Detection. ACM Conference on Information and Knowledge Management. 대한민국
- (2025) FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection. ACM Conference on Information and Knowledge Management. 대한민국
- (2025) MU-OT: Effective and Unified Machine Unlearning with Optimal Transport for Feature Realignment. ACM Conference on Information and Knowledge Management. 대한민국
- (2025) Seeing Through the Blur: Unlocking Defocus Maps for Deepfake Detection. ACM Conference on Information and Knowledge Management. 대한민국
- (2025) From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users. ACM Multimedia Conference. 아일랜드
- (2025) PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting. ACM Multimedia Conference. 아일랜드
- (2025) SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection. ACM Multimedia Conference. 아일랜드
- (2025) DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models. International Conference on Computer Vision. 미국
- (2025) SpecGuard: Spectral Projection-based Advanced InvisibleWatermarking. International Conference on Computer Vision. 미국
- (2025) Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models. International Conference on Computer Vision. 미국
- (2025) HiDF: A Human-Indistinguishable Deepfake Dataset. ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 캐나다
- (2025) Gradient Alignment for Cross-Domain Face Anti-Spoofing. Conference on Computer Vision and Pattern Recognition. 미국
- (2025) Fairness and Robustness in Machine Unlearning. International World Wide Web Conference. 오스트레일리아
- (2025) Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal. International World Wide Web Conference. 오스트레일리아
- (2025) Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset. International World Wide Web Conference. 오스트레일리아
- (2025) High-Fidelity Face Age Transformation via Hierarchical Encoding and Contrastive Learning. ACM SIGAPP Symposium on Applied Computing. 이탈리아
전시/발표회
- (2023) 불멸의 6·25전쟁 영웅, 청년으로 돌아오다 특별 사진전. 대한민국,