8 papers
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
Shih-Yu Lai, Hirozumi Yamaguchi, Shang-Tse Chen +2
Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated learning offers a privacy-resp…
Expanding the Role of Diffusion Models for Robust Classifier Training
Pin-Han Huang, Shang-Tse Chen, Hsuan-Tien Lin
Incorporating diffusion-generated synthetic data into adversarial training (AT) has been shown to substantially improve the training of robust image classifiers. In this work, we e…
Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors
Ren-Wei Liang, Chin-Ting Hsu, Chan-Hung Yu +6
Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive mode…
DRAG: Data Reconstruction Attack using Guided Diffusion
Wa-Kin Lei, Jun-Cheng Chen, Shang-Tse Chen
With the rise of large foundation models, split inference (SI) has emerged as a popular computational paradigm for deploying models across lightweight edge devices and cloud server…
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
Bo-Han Lai, Pin-Han Huang, Bo-Han Kung +1
Lipschitz neural networks are well-known for providing certified robustness in deep learning. In this paper, we present a novel, efficient Block Reflector Orthogonal (BRO) layer th…
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
Zhen-Ting Liu, Shang-Tse Chen
Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defe…