针对生成对抗网络的指纹成员身份与身份推断
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
AI总结：
本文针对生成对抗网络生成的指纹数据集设计身份推断攻击，评估生成式机器学习模型的身份保护脆弱性，验证了攻击在多配置下的有效性及向其他生物识别场景的可扩展性。
摘要：
生成模型作为新型工业革命的潜在催化剂正受到广泛关注。由于自动样本生成可用于解决通常影响学习型生物识别模型的隐私和数据稀缺问题，这类技术在该领域得到了广泛应用。本文通过设计并测试针对由生成对抗网络（GAN）生成的指纹数据集的身份推断攻击，评估了生成式机器学习模型在身份保护方面的脆弱性。实验结果表明，所提出的方案在不同配置下均有效，且可轻松扩展至其他生物识别测量场景。
英文摘要：
Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric models, such technologies became widely spread in this field. In this paper, we assess the vulnerabilities of generative machine learning models concerning identity protection by designing and testing an identity inference attack on fingerprint datasets created by means of a generative adversarial network. Experimental results show that the proposed solution proves to be effective under different configurations and easily extendable to other biometric measurements.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
