发表机构
Information Technologies Institute, Centre for Research and Technology Hellas（信息技术研究所，希腊研究与技术中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究简单外观操纵下面部年龄验证的漏洞，评估七个模型在三个数据集及四种操纵类型下的情况，发现胡茬操纵影响大，不同人口统计特征受影响有差异，还探索了用偏差缓解方法减轻偏差。
AI 中文摘要
在线平台越来越依赖自动年龄估计系统来执行最低年龄政策。针对为此任务设计的基于视觉的模型，人们担心其对未成年人可能用来绕过此类系统的简单外观变化（如画胡子或涂口红）的鲁棒性。在这项工作中，我们通过模拟未成年人可以轻松实现的视觉改变，对年龄验证的鲁棒性进行了系统研究。我们在三个数据集和四种操纵类型上评估了七个模型，包括视觉、视觉语言和多模态大语言模型。有趣的是，在画有胡茬的情况下，高达61%的真阴性被翻转成假阳性。此外，我们研究了不同人口统计特征如何受到此类操纵的影响，发现印度人受胡茬操纵的影响更大，而在所有操纵中女性比男性受影响更大。最后，我们探索了如何在轻量级线性探针设置中使用偏差缓解方法来减轻这些偏差。
英文摘要
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.
