ZK-IMG：通过零知识证明验证图像以对抗虚假信息
ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation
摘要：
在过去的几年里，生成图像的人工智能方法的能力一直在增加，最近的突破使高分辨率，逼真的“deepfake”（人工生成的图像，目的是误导或伤害）成为可能。Deepfakes的兴起有可能造成社会混乱。最近的工作提出了使用ZK-SNARKs（零知识简洁的非交互式知识论证）和证明相机来验证图像是由相机拍摄的。ZK-SNARKs允许非交互地验证图像变换（即，post-hoc），仅具有标准密码硬度假设。不幸的是，这项工作不保护输入隐私，速度慢得不切实际（只在128个$\times$ 128图像上工作），和/或需要自定义加密参数。为了解决这些问题，我们提出了zk-img，一个用于证明图像变换的库，同时隐藏预变换的图像。zk-img允许应用程序开发人员指定高级图像转换。然后，zk-img将透明地将这些规范编译为ZK-SNARKs。为了隐藏输入或输出图像，zk-img将计算ZK-SNARK中图像的哈希值。我们还提出了安全和私密地链接图像变换的方法，它允许任意多个变换。通过结合这些优化，zk-img是第一个能够在商用硬件上安全和私密地转换高清图像的系统。
英文摘要：
Over the past few years, AI methods of generating images have been increasing in capabilities, with recent breakthroughs enabling high-resolution, photorealistic "deepfakes" (artificially generated images with the purpose of misinformation or harm). The rise of deepfakes has potential for social disruption. Recent work has proposed using ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge) and attested cameras to verify that images were taken by a camera. ZK-SNARKs allow verification of image transformations non-interactively (i.e., post-hoc) with only standard cryptographic hardness assumptions. Unfortunately, this work does not preserve input privacy, is impractically slow (working only on 128$\times$128 images), and/or requires custom cryptographic arguments. To address these issues, we present zk-img, a library for attesting to image transformations while hiding the pre-transformed image. zk-img allows application developers to specify high level image transformations. Then, zk-img will transparently compile these specifications to ZK-SNARKs. To hide the input or output images, zk-img will compute the hash of the images inside the ZK-SNARK. We further propose methods of chaining image transformations securely and privately, which allows for arbitrarily many transformations. By combining these optimizations, zk-img is the first system to be able to transform HD images on commodity hardware, securely and privately.
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。
