Seungju Cho (조승주)

Education

• 2021.3 - Present        Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea

• 2018.8 - 2020.8          M.S. (School of Computing), Korea Advanced Institute of Science Technology, South Korea

• 2012.3 - 2018.8          B.S. (Mathematics & Computer Science and Engineering), Sogang University, South Korea

Research Interests

• Adversarial Attack & Defense

Projects

• 2021.02 - 2021.11 : AI facial recognition disturbance technology through physical patterns, The Institute for Security Convergence, KAIST

• 2022.02 - current : Advancement of physically applicable adversarial attack on AI facial recognition models, The Institute for Security Convergence, KAIST

• 2021.02 - current : Anthropocene Study (digital ecology with AI), Ministry of Science and ICT (MSIT)

Publications

• Seungju Cho, T. Jun, B. Oh, D. Kim ,"DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation", International Joint Conference on Neural Networks (IJCNN), 2020.

• M. Kang, T. Tran, Seungju Cho, D. Kim, "CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification", International Joint Conference on Neural Networks (IJCNN), 2021.

• Junyoung Byun, Seungju Cho, Myung-Joon Kwon, Hee-Seon Kim, and  Changick Kim, "Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

• Seungju Cho, Junyoung Byun, Myung-Joon Kwon, Yoonji Kim, and Changick Kim, "Adversarial Training with Channel Attention Regularization", IEEE International Conference on Image Processing (ICIP), 2022. 

• Junyoung Byun, Hyojun Go, Seungju Cho, and Changick Kim, "Exploiting Doudbly Adversarial Examples for Improiving Adversarial Robustness", IEEE International Conference on Image Processing (ICIP), 2022. 

• Minji Son, Myung-Joon Kwon, Hee-Seon Kim, Junyoung Byun, Seungju Cho, and Changick Kim, "Adaptive Warping Network for Transferable Adversarial Attacks", IEEE International Conference on Image Processing (ICIP), 2022. 

• Jinyoung Park, Inyoung Lee, Minseok Son, Seungju Cho, and Changick Kim, "Nowformer : A locally enhanced temporal learner for precipitation nowcasting", Neural Information Processing Systems (NeurIPS) Workshop, 2022

• Jinyoung Park, Minseok Son, Seungju Cho, Inyoung Lee and Changick Kim, "RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts", Neural Information Processing Systems (NeurIPS) Workshop, 2022

• 이인영, 박진영, 손민석, 조승주, 정민기,김창익, "한국형 가강수량 영상 데이터셋과 딥러닝을 활용한 한반도 초단기 기상영상 예측", 대한전자공학회 하계학술대회, 2022.

• 김윤지, 조승주, 권명준, 김창익, "픽셀 드랍을 이용한 레이블을 사용하지 않는 전이 기반 적대적 공격," 대한전자공학회 추계학술대회, 2021.

• 손민지, 권명준, 조승주, 김창익, "탄성변환을 이용한 적대적 예제의 전이성 향상," 대한전자공학회 추계학술대회, 2021.

• 김정수, 박병준, 조승주, 최명애, 박진영, 서형수, 김창익, "트랩 카메라 영상 데이터셋을 활용한 옵티컬 플로우 퓨전 딥러닝 네트워크," 대한전자공학회 추계학술대회, 2021.

Awards & Honors

• Best Student Paper Award, Summer Annual Conference of IEIE 2022

• Best Paper Award, Autumn Annual Conference of IEIE 2021