面部识别系统语境下的对抗样本生成提案
Adversarial Examples: Generation Proposal in the Context of Facial Recognition Systems
AI总结：
本文从攻击者视角提出基于主成分分析组织自编码器潜在空间的方法，调查面部识别系统对对抗样本的脆弱性，旨在制作适用于躲避和冒充攻击的样本，虽未证实特征分离假设，但为该领域开辟了新研究途径。
摘要：
在本文中，我们通过引入一种来自攻击者视角的新方法，调查了面部识别系统对对抗样本呈现出的脆弱性。该技术基于使用由主成分分析组织的自编码器潜在空间。我们旨在分析制作适用于针对最先进系统的躲避和冒充攻击的对抗样本的潜力。我们的初始假设（未得到结果的强力支持）指出，可以在“身份”和“面部表情”特征之间进行分离以产生高质量样本。尽管研究结果不支持该假设，但结果激发了对对抗样本生成的洞察，并为该领域开辟了新的研究途径。
英文摘要：
In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent space, organized with principal component analysis. We intend to analyze the potential to craft adversarial examples suitable for both dodging and impersonation attacks, against state-of-the-art systems. Our initial hypothesis, which was not strongly favoured by the results, stated that it would be possible to separate between the "identity" and "facial expression" features to produce high-quality examples. Despite the findings not supporting it, the results sparked insights into adversarial examples generation and opened new research avenues in the area.
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。
