PulseAugur
实时 13:04:46
English(EN) Transferable Attack against Face Swapping in an Extended Space

新型AIR攻击以增强的视觉质量绕过换脸模型

研究人员开发了一种名为AIR(基于重照明函数的加性身份攻击)的新型可迁移攻击方法,用于绕过换脸(FS)模型。该方法利用重照明和加性扰动来误导主体无关FS模型中的身份提取模块。AIR扩展了攻击空间,能够生成更强大但视觉上自然的对抗性样本,并且在各种基于GAN和扩散的FS模型上,其攻击成功率和图像质量均优于现有方法。 AI

影响 这项研究突显了当前换脸技术的漏洞,并可能促进开发更强大的防御措施,以应对深度伪造操纵。

排序理由 详细介绍针对换脸模型的新攻击方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新型AIR攻击以增强的视觉质量绕过换脸模型

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Mingzhi Lyu, Yi Huang, Jun Xie, Zihao Zhao, Hong Xu, Adams Wai-Kin Kong ·

    Transferable Attack against Face Swapping in an Extended Space

    arXiv:2606.25376v1 Announce Type: new Abstract: Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to privacy and security. Existing protections, including deepfake detection and adversarial perturbation, are either passive re…

  2. arXiv cs.CV TIER_1 English(EN) · Adams Wai-Kin Kong ·

    Transferable Attack against Face Swapping in an Extended Space

    Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to privacy and security. Existing protections, including deepfake detection and adversarial perturbation, are either passive responses or ineffective to unseen subject-agnosti…