9 papers
CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
Jaewon Jung, Haizhong Zheng, Hongsun Jang +3
Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious…
NAVIS: Concurrent Search and Update with Low Position-Seeking Overhead in On-SSD Graph-Based Vector Search
Jaeyong Song, Hongsun Jang, Changmin Shin +4
On-disk graph-based vector search (GVS) has become the dominant approach for serving large-scale vector databases at high recall, but prior systems struggle to sustain concurrent s…
GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading
Jaeyong Song, Seongyeon Park, Hongsun Jang +4
Full-graph training of graph neural networks (GNNs) is widely used as it enables direct validation of algorithmic improvements by preserving complete neighborhood information. Howe…
Piccolo: Large-Scale Graph Processing with Fine-Grained In-Memory Scatter-Gather
Changmin Shin, Jaeyong Song, Hongsun Jang +7
Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This ineff…
A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs
Hongsun Jang, Jaeyong Song, Changmin Shin +4
The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting off…
Pipette: Automatic Fine-grained Large Language Model Training Configurator for Real-World Clusters
Jinkyu Yim, Jaeyong Song, Yerim Choi +4
Training large language models (LLMs) is known to be challenging because of the huge computational and memory capacity requirements. To address these issues, it is common to use a…