6 papers
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
Hongjang Yang, Hyunsik Na, Daeseon Choi
LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability,…
ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering
Chaerin Lee, Sohee Park, Hyunsik Na +1
Recent studies in medical question answering (Medical QA) have actively explored the integration of large language models (LLMs) with biomedical knowledge graphs (KGs) to improve f…
STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
Seong-Gyu Park, Sohee Park, Jisu Lee +2
Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface for inference-time backdoors, whi…
Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
Hajun Kim, Hyunsik Na, Daeseon Choi
As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass b…
IPG: Incremental Patch Generation for Generalized Adversarial Patch Training
Wonho Lee, Hyunsik Na, Jisu Lee +1
The advent of adversarial patches poses a significant challenge to the robustness of AI models, particularly in the domain of computer vision tasks such as object detection. In con…
Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores
Hyunsik Na, Wonho Lee, Seungdeok Roh +2
The advent of convenient and efficient fully unmanned stores equipped with artificial intelligence-based automated checkout systems marks a new era in retail. However, these system…