Hyunsik Na

According to our database, Hyunsik Na authored at least 15 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments.

Hongjang Yang, Hyunsik Na, Daeseon Choi

CoRR, May, 2026

ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering.

Chaerin Lee, Sohee Park, Hyunsik Na, Daseon Choi

CoRR, January, 2026

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio.

Seong-Gyu Park, Sohee Park, Jisu Lee, Hyunsik Na, Daeseon Choi

CoRR, January, 2026

TRACE: Confounder-free Adversarial Fine-tuning for Robust Object Detection.

Wonho Lee, Jisu Lee, Hyunsik Na, Sohee Park, Daeseon Choi

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

2025

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security.

Hajun Kim, Hyunsik Na, Daeseon Choi

CoRR, November, 2025

IPG: Incremental Patch Generation for Generalized Adversarial Patch Training.

Wonho Lee, Hyunsik Na, Jisu Lee, Daeseon Choi

CoRR, August, 2025

Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores.

Hyunsik Na, Wonho Lee, Seungdeok Roh, Sohee Park, Daeseon Choi

CoRR, May, 2025

TrapMI: A Data Protection Method to Resist Model Inversion Attacks in Split Learning.

Hyunsik Na, Daeseon Choi

IEEE Access, 2025

Countering Jailbreak Attacks with Two-Axis Pre-detection and Conditional Warning Wrappers.

Hyunsik Na, Hajun Kim, Dooshik Yoon, Daeseon Choi

Proceedings of the Computer Security - ESORICS 2025, 2025

Adversarial Image Detection for Vision Transformers via Attention Map.

Seonggyu Park, Hyunsik Na, Daeseon Choi

Proceedings of the IEEE International Conference on Advanced Visual and Signal-Based Systems, 2025

2024

Verifiable Facial De-Identification in Video Surveillance.

Sungjune Park, Hyunsik Na, Daeseon Choi

IEEE Access, 2024

Performance Comparison and Visualization of AI-Generated-Image Detection Methods.

Daeeol Park, Hyunsik Na, Daeseon Choi

IEEE Access, 2024

2023

Systematic Evaluation of Robustness Against Model Inversion Attacks on Split Learning.

Hyunsik Na, Yoonju Oh, Wonho Lee, Daeseon Choi

Proceedings of the Information Security Applications - 24th International Conference, 2023

2022

Extracting a Minimal Trigger for an Efficient Backdoor Poisoning Attack Using the Activation Values of a Deep Neural Network.

Hyunsik Na, Daeseon Choi

Proceedings of the WDC@AsiaCCS '22: Proceedings of the 1st Workshop on Security Implications of Deepfakes and Cheapfakes, 2022

2021

Adversarial Attack Based on Perturbation of Contour Region to Evade Steganalysis-Based Detection.

Hyunsik Na, Gwonsang Ryu, Daeseon Choi

IEEE Access, 2021