研究简单化妆如何骗过人脸识别年龄系统，发现61%的未成年可被误判为成年。
Face Age Verification Vulnerabilities Under Simple Appearance Manipulations
- 模拟画胡子、涂口红等简单操作，测试年龄识别模型鲁棒性。
- 画胡茬使61%真实未成年人被错误识别为成年人。
- 印度人和女性受干扰影响更大，适合关注公平性和安全性的读者。
在线平台日益依赖自动化年龄估计算法来执行最低年龄政策。针对基于视觉的此类模型，人们担忧未成年人可通过简单外观改变（如画胡子或涂口红）绕过系统。本文系统研究了年龄验证的鲁棒性，模拟了未成年人可轻松实现的视觉变化。我们在三个数据集上评估了七种模型（包括视觉、视觉-语言及多模态大语言模型），涵盖四种操纵类型。结果显示，在绘制胡茬的情况下，高达61%的真实负例（未成年人）被错误分类为假阳性。此外，我们分析了不同人群受影响程度，发现印度人对胡茬操纵更敏感，而女性在所有操纵下均比男性更易受影响。最后，我们探索在轻量级线性探测设置中使用偏见缓解方法来减轻这些偏差。
原文摘要 · Abstract (English)
Online platforms increasingly rely on automated age estimation systems to enforce minimum-age policies. Focusing on vision-based models designed for this task, concerns arise regarding their robustness to simple appearance changes that underage individuals may use to bypass such systems, such as drawing a mustache or applying lipstick. In this work, we present a systematic study of age verification robustness by simulating visual alterations that can be easily achieved by underage individuals. We evaluate seven models, including vision, vision-language, and multimodal large language models, across three datasets and four manipulation types. Interestingly, under drawn beard stubble, up to 61% of True Negatives are flipped into False Positives. Furthermore, we investigate how different demographics are affected by such manipulations, finding that Indians are more affected by beard stubble manipulations, while females are more affected than males across all manipulations. Finally, we explore how these biases can be mitigated using bias mitigation methodologies in lightweight linear probe settings.
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。