通过分层提示调优对统一人脸攻击检测进行基准测试
Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning
AI总结：
针对统一人脸攻击检测缺乏充分基准与可信分类准则的问题，提出了包含697,347个视频的新基准UniAttackDataPlus，以及基于视觉-语言模型的分层提示调优框架，通过自适应探索多语义空间的分类准则提升检测能力。
摘要：
PAD和FFD被提出分别用于保护人脸数据免受基于物理媒体的呈现攻击和基于数字编辑的Deepfakes侵害。然而，这两个模型的孤立训练显著增加了对未知攻击的脆弱性，加重了部署环境的负担。缺乏一个能同时处理这两类攻击的统一人脸攻击检测模型主要归因于两个因素：（1）缺乏一个足以让模型充分探索的基准。现有的UAD数据集仅包含有限的攻击类型和样本，导致模型应对大量高级威胁的能力受限。鉴于此，通过一种可解释的分层方式，我们提出了迄今为止最广泛、最复杂的伪造技术集合，即UniAttackDataPlus。我们的UniAttackData+包含2,875个身份及其54种对应的伪造样本，共计697,347个视频。（2）缺乏可信的分类准则。当前方法试图在同一语义空间内探索任意准则，但在遇到多样化攻击时这种准则并不存在。因此，我们提出了一种基于视觉-语言模型的分层提示调优框架，该框架能自适应地从不同语义空间探索多种分类准则。具体而言，我们构建了一个VP-TREE来分层探索各种分类规则。然后，通过自适应修剪提示，模型可以选择最合适的提示，引导编码器以从粗到细的方式在不同层级提取判别性特征。最后，为了帮助模型理解视觉空间中的分类准则，我们提出了一个DPI模块，将视觉提示投影到文本编码器，以帮助获得更准确的语义。
英文摘要：
PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively. However, isolated training of these two models significantly increases vulnerability towards unknown attacks, burdening deployment environments. The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors: (1) A benchmark that is sufficient for models to explore is lacking. Existing UAD datasets only contain limited attack types and samples, leading to the model's confined ability to address abundant advanced threats. In light of these, through an explainable hierarchical way, we propose the most extensive and sophisticated collection of forgery techniques available to date, namely UniAttackDataPlus. Our UniAttackData+ encompasses 2,875 identities and their 54 kinds of corresponding falsified samples, in a total of 697,347 videos. (2) The absence of a trustworthy classification criterion. Current methods endeavor to explore an arbitrary criterion within the same semantic space, which fails to exist when encountering diverse attacks. Thus, we present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces. Specifically, we construct a VP-Tree to explore various classification rules hierarchically. Then, by adaptively pruning the prompts, the model can select the most suitable prompts guiding the encoder to extract discriminative features at different levels in a coarse-to-fine manner. Finally, to help the model understand the classification criteria in visual space, we propose a DPI module to project the visual prompts to the text encoder to help obtain a more accurate semantics.
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。
