I-Hsin Chung

adversarial robustness (1) object detection (1) attention mechanism (1) adversarial training (1) model merging (1) model safety (1) deep learning (1) neural network optimization (1) nuclear norm (1) adversarial attack (1) loss function (1) spectral truncation (1) edge device (1) edge computing (1) inference optimization (1) prompt injection (1) multilingual model (1) inference time (1) adversarial attack detection (1) large language model (1)