Zhou, Tong
17 publications
ICLRW
2025
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
ICLR
2024
ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
NeurIPS
2024
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-Level Signature
CVPR
2024
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for mAP and Traffic Scene Understanding