研究人员开发了新的方法来验证身份证件上全息图的真实性，特别是侧重于检测动态欺诈。一篇论文介绍了一个新的数据集 MIDV-DynAttack，该数据集的攻击样本数量增加了两倍，并提出了一种无需动态攻击样本即可进行训练的新型验证方法。第二篇论文提出了两种自监督方法，通过对透明光学可变器件 (OVD) 的时域动力学进行建模来验证其真实性，这对于在开放集场景中击败未知攻击类型至关重要。 AI
影响 这些进展可能带来更安全的身份验证系统，提高欺诈检测能力。
排序理由 该集群包含两篇在 arXiv 上发表的学术论文，详细介绍了新的研究方法。[lever_c_demoted from research: ic=2 ai=0.4]
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2607.06408v1 Announce Type: new Abstract: Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captured videos under uncontrolled conditions. Current sys…
arXiv:2607.06466v1 Announce Type: new Abstract: This paper addresses the remote verification of the authenticity of Optically Variable Devices (commonly known as holograms) on identity documents. Typically placed over the cardholder's photo, these devices provide strong and easil…
This paper addresses the remote verification of the authenticity of Optically Variable Devices (commonly known as holograms) on identity documents. Typically placed over the cardholder's photo, these devices provide strong and easily verifiable security for human inspection but p…
Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captured videos under uncontrolled conditions. Current systems, however, face critical limitations: existi…