用GAN生成高仿真签名伪造样本，提升欺骗验证系统的能力。
Block Induced Signature Generative Adversarial Network (BISGAN): Signature Spoofing Using GANs and Their Evaluation
- 采用带注意力机制的CycleGAN结构生成伪造签名
- 在测试中实现80%至100%的欺骗成功率
- 提出新评估方法衡量伪造样本质量，适合安全研究者
深度学习正被广泛应用于生物特征识别系统。手写签名是常见的身份认证生物特征数据。生成对抗网络（GAN）通过学习真实与伪造签名来生成新的伪造样本。尽管多数GAN设计侧重于强化验证器（判别器），但对生成器产生的伪造质量关注不足。本文提出一种以生成器为核心的GAN架构，旨在生成能有效欺骗签名验证系统的伪造样本。采用融合Inception式模块与注意力头的CycleGAN作为生成器，搭配改进的SigCNN作为判别器。通过一种新训练策略，模型在测试中实现了80%至100%的欺骗成功率。此外，构建了自定义评估方法，用于量化生成伪造样本的质量。本工作强调生成器导向的GAN设计对理解生物特征生成与评估的重要意义。
原文摘要 · Abstract (English)
Deep learning is actively being used in biometrics to develop efficient identification and verification systems. Handwritten signatures are a common subset of biometric data for authentication purposes. Generative adversarial networks (GANs) learn from original and forged signatures to generate forged signatures. While most GAN techniques create a strong signature verifier, which is the discriminator, there is a need to focus more on the quality of forgeries generated by the generator model. This work focuses on creating a generator that produces forged samples that achieve a benchmark in spoofing signature verification systems. We use CycleGANs infused with Inception model-like blocks with attention heads as the generator and a variation of the SigCNN model as the base Discriminator. We train our model with a new technique that results in 80% to 100% success in signature spoofing. Additionally, we create a custom evaluation technique to act as a goodness measure of the generated forgeries. Our work advocates generator-focused GAN architectures for spoofing data quality that aid in a better understanding of biometric data generation and evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。