Membership inference attacks with token-level deduplication on korean language models MG Oh, LH Park, J Kim, J Park, T Kwon IEEE Access 11, 10207-10217, 2023 | 7 | 2023 |
Poster: Adversarial Defense with Deep Learning Coverage on MagNet's Purification LH Park, J Park, S Chung, J Kim, MG Oh, T Kwon Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications …, 2022 | 1 | 2022 |
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training LH Park, J Kim, MG Oh, J Park, T Kwon arXiv preprint arXiv:2402.12187, 2024 | | 2024 |
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships MG Oh, HE Ahn, LH Park, T Kwon arXiv preprint arXiv:2402.12189, 2024 | | 2024 |
마스크 언어 모델의 생성문과 실제 훈련 데이터 분포의 상관성 분석 오명교, 박래현 한국정보과학회 학술발표논문집, 856-858, 2023 | | 2023 |
Improving Adversarial Robustness via Attention J Kim, MG Oh, LH Park, T Kwon Journal of the Korea Institute of Information Security & Cryptology 33 (4 …, 2023 | | 2023 |
On Membership Inference Attacks to Generative Language Models Across Language Domains MG Oh, LH Park, J Kim, J Park, T Kwon International Conference on Information Security Applications, 143-155, 2022 | | 2022 |
계층적 특징추출 모델을 적용한 개인인증용 심전도 신호의 신뢰도 판별 오명교, 이우진, 이현정 한국 HCI 학회 학술대회, 588-596, 2020 | | 2020 |