2 papers
cs.CR2025
LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators
You Li, Guannan Zhao, Yuhao Ju +3
We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against vari…
cs.LG2024
Certifying Global Robustness for Deep Neural Networks
You Li, Guannan Zhao, Shuyu Kong +2
A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and g…