1 citations · 1 across the 9 of their papers we have counts for
10 papers
SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning
Donghwa Kang, Hojun Choe, Doohyun Kim +2
Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by…
QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection
Jinyeong Park, Donghwa Kang, Seunghwan An +4
Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (regio…
Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings
Doohyun Kim, Donghwa Kang, Kyungjae Lee +2
The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversi…
STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers
Donghwa Kang, Doohyun Kim, Sang-Ki Ko +3
Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep op…
Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
Donghwa Kang, Doohyun Kim, Sang-Ki Ko +3
State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: s…
A 2-Stage Model for Vehicle Class and Orientation Detection with Photo-Realistic Image Generation
Youngmin Kim, Donghwa Kang, Hyeongboo Baek
We aim to detect the class and orientation of a vehicle by training a model with synthetic data. However, the distribution of the classes in the training data is imbalanced, and th…
CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection
Woojin Shin, Donghwa Kang, Byeongyun Park +3
Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrent…
Real Time Scheduling Framework for Multi Object Detection via Spiking Neural Networks
Donghwa Kang, Woojin Shin, Cheol-Ho Hong +4
Given the energy constraints in autonomous mobile agents (AMAs), such as unmanned vehicles, spiking neural networks (SNNs) are increasingly favored as a more efficient alternative…
BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks
Woojin Shin, Donghwa Kang, Daejin Choi +3
Multi-object tracking (MOT) aims to construct moving trajectories for objects, and modern multi-object trackers mainly utilize the tracking-by-detection methodology. Initial approa…
AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network
Donghwa Kang, Youngmoon Lee, Eun-Kyu Lee +3
In the training and inference of spiking neural networks (SNNs), direct training and lightweight computation methods have been orthogonally developed, aimed at reducing power consu…