伪造手写签名的生成对抗网络
Maciej Marcinowski-Prażmowski1
1Forensics, Institute of Law, University of Silesia, Katowice, Poland.
Journal of forensic sciences
|December 4, 2024
概括
生成型人工智能可以创建现实的假签名. 传统的手写分析仍然可以检测这些深度假冒伪造,主要是由于视觉质量较低,但未来的AI改进可能会带来挑战.
科学领域:
- 计算机科学 计算机科学
- 法医科学 法医科学 法医科学
背景情况:
- 生成性人工智能,特别是生成性对抗性网络 (GANs),正在迅速发展,导致越来越复杂的深度假冒.
- 传统的法医手写检查方法通常应用于数字文档,但在没有数字法医集成的情况下,可能对人工智能产生的伪造不足.
研究的目的:
- 调查传统手写检查技术对由翻译GAN生成的深度假冒签名的有效性.
- 确定当前的法医方法是否能够识别GAN制造的假冒,并评估其局限性.
主要方法:
- 开发一个翻译性的生成对抗网络 (GAN),从有限的真实实例中创建合成的手写签名.
- 应用传统的手写检查方法来分析生成的深伪签名.
- 评估传统方法在检测GAN制造的假冒中发现的歧视性特征.
主要成果:
- 传统的手写检查方法证明足以识别可能导致拒绝GAN生成的伪造的特征.
- 主要的区分特征与合成签名的视觉质量较低有关.
- 该研究承认,未来GAN的进步可能会提高产生的伪造品的视觉真实性.
结论:
- 传统的法医手写分析仍然是当前GAN制造的签名伪造的有效工具.
- 效率依赖于检测从生成过程中产生的视觉工件.
- 预测未来的挑战,因为人工智能产生的伪造品在视觉上变得更加精致.
相关概念视频
01:16Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
01:17Sign Test for Matched Pairs
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in value between...
To conduct the sign test, we first calculate the differences in value between...