arXiv subjects

JunKyu Lee

Publications and source records attributed to JunKyu Lee.

7 recordsLinked to original sources

arXiv2025

SGuard-v1: Safety Guardrail for Large Language Models

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component, ContentFilter, is trained to identify safety risks in LLM prompts and responses in accordance with the MLCommons hazard taxonomy, a comprehensive framework for trust and safety assessment of AI. The second component, JailbreakFilter, is trained with a carefully designed curriculum over integrated datasets and findings from prior work on adversarial prompting, covering 60 major attack types while mitigating false-unsafe classification. SGuard-v1 is built on the 2B-parameter Granite-3.3-2B-Instruct model that supports 12 languages. We curate approximately 1.4 million training instances from both collected and synthesized data and perform instruction tuning on the base model, distributing the curated data across the two component according to their designated functions. Through extensive evaluation on public and proprietary safety benchmarks, SGuard-v1 achieves state-of-the-art safety performance while remaining lightweight, thereby reducing deployment overhead. SGuard-v1 also improves interpretability for downstream use by providing multi-class safety predictions and their binary confidence scores. We release the SGuard-v1 under the Apache-2.0 License to enable further research and practical deployment in AI safety.

cs.CL↗

arXiv2024

Mitigating scalability challenges in LUT-based neural networks via pruning optimisations

Modern deep neural networks heavily rely on a large number of multiply-accumulate operations, which constitute the predominant computational cost. To address this, Look-Up Table (LUT)-based matrix multiplications have emerged as a promising alternative for reducing the computational cost and time of the multiply-accumulate operations in a neural network. However, the LUT-based neural network still faces the scalability challenge due to the inherent limitations of LUT-based matrix multiplication. To mitigate these scalability limitations, this paper proposes a scalable and energy-efficient LUT-based approximate matrix multiplication unit (LUT-MU) constituting the basic component of the neural networks by integrating a pruning strategy on the MADDNESS algorithm, a LUT-based matrix multiplication methodology. With increasing problem size and precision demands in matrix multiplication, our proposed LUT-MU architecture effectively constrains resource expansion. The case study shows that deploying our LUT-MU in neural network architectures, including fully connected layers (MNIST) and ResNets (CIFAR-10, ImageNet)-on XCZU7EV and XCZU19EG FPGAs, produces up to $1.6 \times$ throughput improvement and $4.2 \times$ energy efficiency gains over mainstream CUDA-based network implementations, and $1.8\times$ energy efficiency compared to leading quantised neural network implementations, with moderate impact on accuracy. Compared to original MADDNESS-based neural networks, our LUT-MU shows $1.3$ to $2.6\times$ resource savings based on various resolution configuration settings of MADDNESS.

cs.AR↗

arXiv2023

A case study on latency, bandwidth and energy efficiency of mobile 5G and YouTube Edge service in London. Why the 5G ecosystem and energy efficiency matter?

The advancements in 5G mobile networks and Edge computing offer great potential for services like augmented reality and Cloud gaming, thanks to their low latency and high bandwidth capabilities. However, the practical limitations of achieving optimal latency on real applications remain uncertain. This paper aims to investigate the actual latency and bandwidth provided by 5G Networks and YouTube Edge service in London, UK. We analyze how latency and bandwidth differ between 4G LTE and 5G networks and how the location of YouTube Edge servers impacts these metrics. Our research reveals over 10 significant observations and implications, indicating that the primary constraints on 4G LTE and 5G capabilities are the ecosystem and energy efficiency of mobile devices down-streaming data. Our study demonstrates that to fully unlock the potential of 5G and it's applications, it is crucial to prioritize efforts aimed at improving the ecosystem and enhancing the energy efficiency.

cs.NI↗

arXiv2023

Vortex Feature Positioning: Bridging Tabular IIoT Data and Image-Based Deep Learning

Tabular data from IIoT devices are typically analyzed using decision tree-based machine learning techniques, which struggle with high-dimensional and numeric data. To overcome these limitations, techniques converting tabular data into images have been developed, leveraging the strengths of image-based deep learning approaches such as Convolutional Neural Networks. These methods cluster similar features into distinct image areas with fixed sizes, regardless of the number of features, resembling actual photographs. However, this increases the possibility of overfitting, as similar features, when selected carefully in a tabular format, are often discarded to prevent this issue. Additionally, fixed image sizes can lead to wasted pixels with fewer features, resulting in computational inefficiency. We introduce Vortex Feature Positioning (VFP) to address these issues. VFP arranges features based on their correlation, spacing similar ones in a vortex pattern from the image center, with the image size determined by the attribute count. VFP outperforms traditional machine learning methods and existing conversion techniques in tests across seven datasets with varying real-valued attributes.

cs.CV↗

arXiv2022

ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy

This paper analyzes the effects of dynamically varying video contents and detection latency on the real-time detection accuracy of a detector and proposes a new run-time accuracy variation model, ROMA, based on the findings from the analysis. ROMA is designed to select an optimal detector out of a set of detectors in real time without label information to maximize real-time object detection accuracy. ROMA utilizing four YOLOv4 detectors on an NVIDIA Jetson Nano shows real-time accuracy improvements by 4 to 37% for a scenario of dynamically varying video contents and detection latency consisting of MOT17Det and MOT20Det datasets, compared to individual YOLOv4 detectors and two state-of-the-art runtime techniques.

cs.CV↗

arXiv2021

Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques

Deep learning is pervasive in our daily life, including self-driving cars, virtual assistants, social network services, healthcare services, face recognition, etc. However, deep neural networks demand substantial compute resources during training and inference. The machine learning community has mainly focused on model-level optimizations such as architectural compression of deep learning models, while the system community has focused on implementation-level optimization. In between, various arithmetic-level optimization techniques have been proposed in the arithmetic community. This article provides a survey on resource-efficient deep learning techniques in terms of model-, arithmetic-, and implementation-level techniques and identifies the research gaps for resource-efficient deep learning techniques across the three different level techniques. Our survey clarifies the influence from higher to lower-level techniques based on our resource-efficiency metric definition and discusses the future trend for resource-efficient deep learning research.

cs.LG↗

arXiv2021

TOD: Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge

Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise Object Detector (TOD) which maximises the real-time object detection accuracy on an edge device by selecting an appropriate Deep Neural Network (DNN) on the fly with negligible computational overhead. TOD makes two key contributions over the state of the art: (1) TOD leverages characteristics of the video stream such as object size and speed of movement to identify networks with high prediction accuracy for the current frames; (2) it selects the best-performing network based on projected accuracy and computational demand using an effective and low-overhead decision mechanism. Experimental evaluation on a Jetson Nano demonstrates that TOD improves the average object detection precision by 34.7 % over the YOLOv4-tiny-288 model on average over the MOT17Det dataset. In the MOT17-05 test dataset, TOD utilises only 45.1 % of GPU resource and 62.7 % of the GPU board power without losing accuracy, compared to YOLOv4-416 model. We expect that TOD will maximise the application of edge devices to real-time object detection, since TOD maximises real-time object detection accuracy given edge devices according to dynamic input features without increasing inference latency in practice.

cs.DC↗