TL;DR
This paper upgrades fingerprint evidence from a source-boundary transferability heuristic to an explicit ownership-separation objective, formulate fingerprint construction as a decision difference region (DDR) search problem and solve it with two non-invasive variants, giving owners a tunable trade-off between construction cost and verification confidence.
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 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.
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.
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.
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.
This review consolidates signature verification work involving offline, online, mobile, contactless, and in-air verification and presents an original, practical taxonomy for over 50 selected works and standards.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
