collaborators

6 papers

cs.CR2026

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…

cs.CV2026

No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings

Joonsung Jeon, Woo Jae Kim, Suhyeon Ha +2

Latent diffusion models have achieved remarkable success in high-fidelity text-to-image generation, but their tendency to memorize training data raises critical privacy and intelle…

cs.LG2026

Discovering Universal Activation Directions for PII Leakage in Language Models

Leo Marchyok, Zachary Coalson, Sungho Keum +2

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are re…

cs.CV2025

AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

Woo Jae Kim, Kyu Beom Han, Yoonki Cho +4

As Neural Radiance Fields (NeRFs) have emerged as a powerful tool for 3D scene representation and novel view synthesis, protecting their intellectual property (IP) from unauthorize…

cs.CR2025

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…

cs.CV2025

AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption

Joonsung Jeon, Woo Jae Kim, Suhyeon Ha +2

The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversari…