2021/11/12 by Lukas Struppek, Dominik Hintersdorf, Daniel Neider +1 · 2 voices · 2 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Adversarial Robustness in Machine Learning #Digital Media Forensic Detection #cs.CR #cs.CV #cs.LG
paper · pdf · doi:10.1145/3531146.3533073
arxiv published 2021/11/12 · openalex publication_date 2022/06/20 · arxiv updated 2024/07/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
Apple recently revealed its deep perceptual hashing system NeuralHash to detect child sexual abuse material (CSAM) on user devices before files are uploaded to its iCloud service. Public criticism quickly arose regarding the protection of user privacy and the system’s reliability. In this paper, we present the first comprehensive empirical analysis of deep perceptual hashing based on NeuralHash. Specifically, we show that current deep perceptual hashing may not be robust. An adversary can manipulate the hash values by applying slight changes in images, either induced by gradient-based approaches or simply by performing standard image transformations, forcing or preventing hash collisions. Such attacks permit malicious actors easily to exploit the detection system: from hiding abusive material to framing innocent users, everything is possible. Moreover, using the hash values, inferences can still be made about the data stored on user devices. In our view, based on our results, deep perceptual hashing in its current form is generally not ready for robust client-side scanning and should not be used from a privacy perspective.1