Xiaoxuan Lou — accepted AI-conference papers

2023

Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only

Kangjie Chen, Xiaoxuan Lou, Guowen Xu, Jiwei Li, Tianwei Zhang

ICLR 2023top-5%

Multi-label models have been widely used in various applications including image annotation and object detection. The fly in the ointment is its inherent vulnerability to backdoor attacks due to the adoption of deep learning techniques. However, all existing backdoor attacks exclusively require to m…

Cited by 47 Source ↗PDF ↗Scholar ↗

2022

NASPY: Automated Extraction of Automated Machine Learning Models

Xiaoxuan Lou, Shangwei Guo, Jiwei Li, Yaoxin Wu, Tianwei Zhang

ICLR 2022spotlight

We present NASPY, an end-to-end adversarial framework to extract the networkarchitecture of deep learning models from Neural Architecture Search (NAS). Existing works about model extraction attacks mainly focus on conventional DNN models with very simple operations, or require heavy manual analysis…

Cited by 6 Source ↗PDF ↗Scholar ↗