3 citations · 5 across the 10 of their papers we have counts for
6 papers · 1 filter
SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs
Hanna Kim, Jian Cui, Minkyoo Song +4
Script-based malware remains a prevalent attack technique. These scripts often contain indicators of compromise (IOCs) that provide actionable threat intelligence. However, statica…
SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills
Youngduk Kim, Minkyoo Song, Seungwon Shin
Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills, which pair natural-language specifications (SKILL.md) with executable s…
Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG
Minkyoo Song, Jaehan Kim, Myungchul Kang +3
Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a kn…
: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
Wonwoo Choi, Minjae Seo, Minkyoo Song +3
The rapid evolution of text-to-image (T2I) models has enabled high-fidelity visual synthesis on a global scale. However, these advancements have introduced significant security ris…
Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
Jaehan Kim, Minkyoo Song, Seungwon Shin +1
Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechan…
When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
Hanna Kim, Minkyoo Song, Seung Ho Na +2
Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting with various tools. These LLM agents are often pair…