3 papers
cs.CR2025
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
Tong Zhou, Shijin Duan, Gaowen Liu +4
Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks th…
cs.CR2024
Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
Ruyi Ding, Tong Zhou, Lili Su +3
Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specific…
cs.CR2024
TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
Ziyu Liu, Tong Zhou, Yukui Luo +1
Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or…