Byunggill Joe

Educations

• Ph.D. Candidate,  Korea Advanced Institute of Science and Technology, Mar. 2017 - Current, Advisor: Insik Shin.

• MS,  Korea Advanced Institute of Science and Technology, Mar. 2015 - Feb. 2017, Advisor: Insik Shin.

• BS,  Korea Advanced Institute of Science and Technology, Mar. 2011 - Feb. 2015. 

Publications

      International Conferences

• Online Evasion Attacks on Recurrent Models: The Power of Hallucinating the Future
  Byunggill Joe, Insik Shin, Jihun Hamm
  In the 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI '22), Vienna, Austria, July 2022.

• OBFSCURO: A Commodity Obfuscation Engine on Intel SGX
  Adil Ahmad*, Byunggill Joe*, Yuan Xiao, Yinqian Zhang, Insik Shin, Byoungyoung Lee
  Proceedings of the 2019 Network and Distributed System Security Symposium (NDSS '19), San Diego, CA, US, February 2019.

* co-first authors 

• Enhancing Memory Error Detection for Large-Scale Applications and Fuzz Testing

Wookhyun Han, Byunggill Joe, Byoungyoung Lee, Chengyu Song, Insik Shin

Proceedings of the 2018 Network and Distributed System Security Symposium (NDSS '18), San Diego, CA, US, February 2018. 

      Journals

• Backdoor Attack on Machine Learning Models of Electronic Health Records: Exploiting Missing Value Patterns
  Byunggill Joe*, Yonghyeon Park*, Jihun Hamm, Insik Shin, Jiyeon Lee
  JMIR Medical Informatics, 2022.
  * co-first authors

• Tapsnoop: Leveraging tap sounds to infer tapstrokes on touchscreen devices
  Hyosu Kim, Byunggill Joe, Yunxin Liu
  IEEE Access’20, Volume: 8.

• Cardiac auscultation using smartphones: pilot study
  Si-Hyuck Kang, Byunggill Joe, Yeonyee Yoon, Goo-Yeong Cho, Insik Shin, Jung-Won Suh
  JMIR Mhealth Uhealth. February 2018.

     Submitted Papers

• ARCLU: Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
  Byunggil Joe, Jihun Hamm, Sooel Son, Sung Ju Hwang, Insik Shin
  Under Review, Computer & Security.

     Workshop & Miscellaneous

• Missing Pattern Based Backdoor Attack on Medical Machine Learning Model
  Yonghyeon Park, Byunggill Joe, Jiyeon Lee, Minwoo Jeong, Insik Shin
  Workshop on Dependable and Secure Computing, 2021.

• Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
  Byunggill Joe, Akshay Mehra, Insik Shin, Jihun Hamm
  Workshop on Trustworthy AI for Healthcare, AAAI 2021.

• Virtualization System Framework for Usability and Performance Analysis on Embedded Systems
  Wookhyun Han, Jaewoo Lee, Byunggil Joe, Insik Shin
  2016년 한국군사과학기술학회 종합학술대회 특별세션.

• TapSnoop - Inferring Tapstrokes from Listening to Tap Sound on Mobile Devices
  Hyosu Kim, Daehyeok Kim, Byunggill Joe, Yunxin Liu, Insik Shin
  Poster session of the 14th International Conference on Mobile Systems, Applications and Services (MobiSys '16), Singapore, June 2016.

• Preventing malicious monitoring through SMS permission segmentation in Android
  Eunchan Kim, Jaebaek Seo, Byunggil Joe, Insik Shin
  Korea Computer Congress, Jeju, Korea, June 2015.

• GPGPU Parallelization Techniques for Redundancy Elimination Algorithm
  Byunggil Joe, Dae R. Jeong, Jiyeon Lee, Insik Shin
  Korean Institute of Information Scientists and Engineers, Korea, December 2014. 

Awards

• Qualcomm Innovation Award, 2019
  Byunggill Joe, Sungju Hwang, Insik Shin.

• The 24th Samsung HumanTech paper award, bronze, 2018
  Hyosu Kim, Daehyeok Kim, and Byunggill Joe.

• Qualcomm Innovation Award, 2016
  Hyosu Kim, Daehyeok Kim, Byunggill Joe.

• Undergraduate student Best Paper Award, Korea Institute of Information Scientists and Engineers, 2015
  Byunggil Joe, Dae R. Jeong, Jiyeon Lee, Insik Shin.