Red Teaming

Agentic AI systems are powerful but remain vulnerable to adversarial manipulation and jailbreaking. We advance their robustness by continuously probing and debugging them through red teaming. This raises the following question.

How do we train red agents that continuously debug target AI systems for hardening?

Keywords

  • Agentic AI
  • Reinforcement Learning

6 Related Publications

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
Junyoung Park, Namgyu Park, Sechan Lee, Yoon-Chan Jhi, Jihoon Cho, Sangdon Park
2026
Can We Stop Malicious AI? KILLBENCH: A Benchmark for External AI Kill Switch Feasibility
Sechan Lee, Hyounghun Kim, Sangdon Park
2026
The Illusion of Rust Safety: Detecting Modular Unsafe Functions with LLMs
Xiang Cheng, Fan Sang, Yibin Yang, Hang Zhang, Sangdon Park, Xiaokuan Zhang, Taesoo Kim
The ACM Conference on Computer and Communications Security (CCS), 2026
CCS
LLM Watermark Evasion via Bias Inversion
Jeongyeon Hwang, Sangdon Park, Jungseul Ok
International Conference on Machine Learning (ICML), 2026
ICML
Ruby: Unmasking Unsafe Rust in Stripped Binaries via Machine Learning
Xiang Cheng*, Sangdon Park*, HyungSeok Han, Xiaokuan Zhang, Taesoo Kim
International Conference on Dependable Systems and Networks (DSN), 2026
ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
Taesoo Kim, HyungSeok Han, Soyeon Park, Dae R. Jeong, Dohyeok Kim, Dongkwan Kim, Eunsoo Kim, Jiho Kim, Joshua Wang, Kangsu Kim, Sangwoo Ji, Woosun Song, Hanqing Zhao, Andrew Chin, Gyejin Lee, Kevin Stevens, Mansour Alharthi, Yizhuo Zhai, Cen Zhang, Joonun Jang, Yeongjin Jang, Ammar Askar, Dongju Kim, Fabian Fleischer, Jeongin Cho, Junsik Kim, Kyungjoon Ko, Insu Yun, Sangdon Park, Dowoo Baik, Haein Lee, Hyeon Heo, Minjae Gwon, Minjae Lee, Minwoo Baek, Seunggi Min, Wonyoung Kim, Yonghwi Jin, Younggi Park, Yunjae Choi, Jinho Jung, Gwanhyun Lee, Junyoung Jang, Kyuheon Kim, Yeonghyeon Cha, Youngjoon Kim
2025
🏆 DARPA AIxCC Winner - $(4+2)M Award