Efficient and robust DNN model fingerprint with decision difference regions identification

Digital Forensic Detection of Forged Driver's Licenses Using Optimized ResNet50 and Handcrafted Feature Baselines

Automated forged driver's license detection is important for digital identity verification, but many prior studies are difficult to compare because they use different datasets, preprocessing pipelines, and evaluation protocols. This paper presents a controlled comparison of handcrafted and deep learning pipelines for b...

A Harmless Owner-Specific Verification Scheme for DNN Copyright Protection

A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification

A Robust watErMArk-based fingeRprint frameworK for GNNs, named REMARK, which first generates carefully crafted in-distribution watermark graphs that maximize output differences between GNN models, thus mitigating OOD-induced performance degradation.

Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

TRIM (Trigger Removal by Identifying Manipulated Regions), a deployment-oriented black-box defense that detects and selectively removes backdoor triggers at inference time without requiring model internals, training data, or clean samples, is proposed.

Lattice-Quantization Identity Watermarking for Deep Neural Network Ownership Protection

This work proposes a novel lattice quantization-based backdoor watermarking framework for DNNs in black-box settings that embeds the owner’s identity into trigger samples via lattice quantization index modulation, achieving identity encoding while maintaining trigger imperceptibility.

End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery

This paper proposes a new sign-recovery algorithm that achieves higher sign-recovery accuracy than the existing method, and enables efficient sign recovery even for trained models, and demonstrates end-to-end model extraction from models trained on MNIST and Fashion-MNIST.