Juhee Kim
Since: 2020.03
Contact: kimjuhi96@snu.ac.kr
Publications
Agent Data Injection Attacks are Realistic Threats to AI Agents
arXiv Preprint 2026
Woohyuk Choi*, Juhee Kim*, Taehyun Kang, Jihyeon Jeong, Luyi Xing, and Byoungyoung Lee (* co-first authors)
DualView: Preventing Indirect Prompt Injection in Personal AI Agents
arXiv Preprint 2026
Juhee Kim*, Woohyuk Choi*, Taehyun Kang, Youngmin Kim, and Byoungyoung Lee (* co-first authors)
SoK: Attack and Defense Landscape of Agentic AI Systems
USENIX Security Symposium (Security) 2026
Juhee Kim, Wenbo Guo, and Dawn Song
DMGuard: Safeguarding Kernels from Physical Page Use-After-Free Vulnerabilities
USENIX Security Symposium (Security) 2026
Juhee Kim*, Jaeyoung Chung*, Dae R. Jeong, and Byoungyoung Lee (* co-first authors)
TikTag: Breaking ARM's Memory Tagging Extension with Speculative Execution
IEEE Symposium on Security and Privacy (SP) 2025
Juhee Kim, Jinbum Park, Sihyun Roh, Jaeyoung Chung, Youngjoo Lee, Taesoo Kim, and Byoungyoung Lee
Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
arXiv Preprint 2025
Juhee Kim*, Woohyuk Choi*, and Byoungyoung Lee (* co-first authors)
PeTAL: Ensuring Access Control Integrity against Data-only Attacks on Linux
ACM Conference on Computer and Communications Security (CCS) 2024
Juhee Kim, Jinbum Park, Yoochan Lee, Chengyu Song, Taesoo Kim, and Byoungyoung Lee
Bypassing ARM's Memory Tagging Extension with a Side-Channel Attack
BlackHat USA 2024
Juhee Kim, Jinbum Park, Sihyun Roh, Jaeyoung Chung, Youngjoo Lee, Taesoo Kim, and Byoungyoung Lee
Chancel: Efficient Multi-client Isolation Under Adversarial Programs
Network and Distributed System Security Symposium (NDSS) 2021
Adil Ahmad, Juhee Kim, Jaebaek Seo, Insik Shin, Pedro Fonseca, and Byoungyoung Lee