Robustness and Collision-Resistance of PhotoDNA
DOI:
https://doi.org/10.13052/jcsm2245-1439.1339Keywords:
Robust hash, perceptual hash, CSAN detectionAbstract
PhotoDNA is a widely utilized hash designed to counteract Child Sexual Abuse Material (CSAM). However, there has been a scarcity of detailed information regarding its performance. In this paper, we present a comprehensive analysis of its robustness and susceptibility to false positives, along with fundamental insights into its structure. Our findings reveal its resilience to common image processing techniques like lossy compression. Conversely, its robustness is limited when confronted with cropping. Additionally, we propose recommendations for enhancing the algorithm or optimizing its application. This work is an extension on our paper [21].
Downloads
References
Ross Anderson. Chat control or child protection? arXiv preprint arXiv:2210.08958, 2022.
Uwe Breidenbach, Martin Steinebach, and Huajian Liu. Privacy-enhanced robust image hashing with bloom filters. In Melanie Volkamer and Christian Wressnegger, editors, ARES 2020: The 15th International Conference on Availability, Reliability and Security, Virtual Event, Ireland, August 25–28, 2020, pages 56:1–56:10. ACM, 2020.
Olena Buchko et al. Classification of confidential images using neural hash. NaUKMA Research Papers Computer Science, 5:68–71, 2022.
Veena Desai and DH Rao. Image hash using neural networks. International Journal of Computer Applications, 63(22), 2013.
Andrea Drmic, Marin Silic, Goran Delac, Klemo Vladimir, and Adrian S. Kurdija. Evaluating robustness of perceptual image hashing algorithms. In 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pages 995–1000. IEEE, 2017.
Ling Du, Anthony T.S. Ho, and Runmin Cong. Perceptual hashing for image authentication: A survey. Signal Processing: Image Communication, 81:115713, 2020.
Hany Farid. Reining in online abuses. Technology & Innovation, 19(3):593–599, 2018.
Hany Farid. An overview of perceptual hashing. Journal of Online Trust and Safety, 1(1), 2021.
Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.
Marius Leon Hammann, Martin Steinebach, Huajian Liu, and Niklas Bunzel. Predicting positions of flipped bits in robust image hashes. Electronic Imaging, 35:375–1, 2023.
Qingying Hao, Licheng Luo, Steve TK Jan, and Gang Wang. It’s not what it looks like: Manipulating perceptual hashing based applications. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, pages 69–85, 2021.
J Langston. How photodna for video is being used to fight online child exploitation. Combating child pornography: Steps are needed to ensure that tips to law enforcement are useful and forensic examinations are cost effective, 2018.
Hee-Eun Lee, Tatiana Ermakova, Vasilis Ververis, and Benjamin Fabian. Detecting child sexual abuse material: A comprehensive survey. Forensic Science International: Digital Investigation, 34:301022, 2020.
Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. Microsoft COCO: common objects in context. CoRR, abs/1405.0312, 2014.
Muhammad Shahroz Nadeem, Virginia NL Franqueira, and Xiaojun Zhai. Privacy verification of photodna based on machine learning. 93y42, 2019.
Dat Tien Nguyen, Firoj Alam, Ferda Ofli, and Muhammad Imran. Automatic image filtering on social networks using deep learning and perceptual hashing during crises.
Jonathan Prokos, Tushar M. Jois, Neil Fendley, Roei Schuster, Matthew Green, Eran Tromer, and Yinzhi Cao. Squint hard enough: Evaluating perceptual hashing with machine learning. Cryptology ePrint Archive, Paper 2021/1531, 2021. https://eprint.iacr.org/2021/1531.
Chuan Qin, Enli Liu, Guorui Feng, and Xinpeng Zhang. Perceptual image hashing for content authentication based on convolutional neural network with multiple constraints. IEEE Transactions on Circuits and Systems for Video Technology, 31(11):4523–4537, 2020.
Aditya Singh, Mayank Vatsa, and Richa Singh. Photo dna. 2020.
Martin Steinebach. Robust hashing for efficient forensic analysis of image sets. In Pavel Gladyshev and Marcus K. Rogers, editors, Digital Forensics and Cyber Crime, volume 88 of Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pages 180–187. Springer Berlin Heidelberg, Berlin, Heidelberg, 2012.
Martin Steinebach. An analysis of photodna. In Proceedings of the 18th International Conference on Availability, Reliability and Security, ARES 2023, Benevento, Italy, 29 August 2023- 1 September 2023, pages 44:1–44:8. ACM, 2023.
Martin Steinebach. Erkennung von kindesmissbrauch in medien: Methoden und ihre herausforderungen. Datenschutz und Datensicherheit-DuD, 47(4):225–228, 2023.
Martin Steinebach, Tiberius Berwanger, and Huajian Liu. Towards image hashing robust against cropping and rotation. In Proceedings of the 17th International Conference on Availability, Reliability and Security, pages 1–7, 2022.
Martin Steinebach, Tiberius Berwanger, and Huajian Liu. Image hashing robust against cropping and rotation. Journal of Cyber Security and Mobility, pages 129–160, 2023.
Martin Steinebach, Karol Gotkowski, and Hujian Liu. Fake news detection by image montage recognition. In Proceedings of the 14th International Conference on Availability, Reliability and Security, pages 1–9, New York, NY, USA, 2019. ACM.
Martin Steinebach, Huajian Liu, and York Yannikos. Forbild: Efficient robust image hashing. In Media Watermarking, Security, and Forensics 2012, volume 8303, pages 195–202. SPIE, 2012.
Martin Steinebach, Huajian Liu, and York Yannikos. Efficient cropping-resistant robust image hashing. In 2014 Ninth International Conference on Availability, Reliability and Security, pages 579–585. IEEE, 2014.
Martin Steinebach, Huajian Liu, and York Yannikos. Facehash: Face detection and robust hashing. In Pavel Gladyshev, Andrew Marrington, and Ibrahim Baggili, editors, Digital Forensics and Cyber Crime, volume 132 of Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pages 102–115. Springer International Publishing, Cham, 2014.
Martin Steinebach, Sebastian Lutz, and Huajian Liu. Privacy and robust hashes: Privacy-preserving forensics for image re-identification. Journal of Cyber Security and Mobility, pages 111–140, 2020.
Lukas Struppek, Dominik Hintersdorf, Daniel Neider, and Kristian Kersting. Learning to break deep perceptual hashing: The use case neuralhash. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 58–69, 2022.
Rui Sun and Wenjun Zeng. Secure and robust image hashing via compressive sensing. Multimedia Tools and Applications, 70, 06 2012.
Zhenjun Tang, Lv Chen, Xianquan Zhang, and Shichao Zhang. Robust image hashing with tensor decomposition. IEEE Transactions on Knowledge and Data Engineering, 31(3):549–560, 2019.
Zhenjun Tang, Fan Yang, Liyan Huang, and Xianquan Zhang. Robust image hashing with dominant dct coefficients. Optik, 125(18):5102–5107, 2014.
Zhenjun Tang, Xianquan Zhang, Xuan Dai, Jianzhong Yang, and Tianxiu Wu. Robust image hash function using local color features. AEU – International Journal of Electronics and Communications, 67(8):717–722, 2013.
Shaharyar Ahmed Khan Tareen and Zahra Saleem. A comparative analysis of sift, surf, kaze, akaze, orb, and brisk. In 2018 International conference on computing, mathematics and engineering technologies (iCoMET), pages 1–10. IEEE, 2018.
Rebekka Weiß and Simran Mann. Bitkom on the eu proposal on chat control. Policy, 49(30):27576–214, 2022.
Christian Winter, Martin Steinebach, and York Yannikos. Fast indexing strategies for robust image hashes. Digital Investigation, 11:S27–S35, 2014.
Bian Yang, Fan Gu, and Xiamu Niu. Block mean value based image perceptual hashing. In 2006 International Conference on Intelligent Information Hiding and Multimedia, pages 167–172. IEEE, 2006.
Christoph Zauner, Martin Steinebach, and Eckehard Hermann. Rihamark: perceptual image hash benchmarking. In Nasir D. Memon, Jana Dittmann, Adnan M. Alattar, and Edward J. Delp III, editors, Media Watermarking, Security, and Forensics III, SPIE Proceedings, page 78800X. SPIE, 2011.
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Journal of Cyber Security and Mobility
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
