Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
Open accessAbstract
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
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The newest edition of NeuralHash that we experimented with was still not robust to filtering, rotating, and mirroring, similar to the first edition experimented in [11][16].
“Surprisingly, the newest edition of NeuralHash that we experimented with was still not robust to filtering, rotating, and mirroring, similar to the first edition experimented in [11][16].”
From Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks (2024) · cites this paper as [16]
Section 5 (pp. 8–9) reports that the NeuralHash version studied was susceptible to rotation and image flipping (mirroring). It also tests color and contrast changes, but does not establish a general lack of robustness to filtering. The claim about the newest edition is the citing authors’ own result, not a finding attributed to this source. (LLM, conf=0.83)
Experimental — accuracy not yet measuredPhotoDNA is not robust to filtering, rotating, resizing, mirroring, bordering, and cropping.
“- PhotoDNA is not robust to: filtering, rotating, resizing, mirroring, bordering, cropping;”
From Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks (2024) · cites this paper as [16]
Section 5 (pp. 8–9) tests these kinds of transformations on NeuralHash, not PhotoDNA. The passages mentioning PhotoDNA in Sections 2.1 (p. 2) and 7 (p. 11) do not address its robustness to filtering, rotation, resizing, mirroring, borders, or cropping. A search for PhotoDNA and transformation robustness found no passage establishing the attributed claim. (LLM, conf=0.77)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · see citing works
A Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623 · see citing works
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · see citing works
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708 · see citing works
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · see citing works
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332 · see citing works
Dimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336 · see citing works
Approximate nearest neighbors: towards removing the curse of dimensionality
Indyk, P., & Motwani, R. (1998) · Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98 · doi:10.1145/276698.276876 · Cited by 4,188 · see citing works
(1999) · Cited by 3,186 · see citing works
One Pixel Attack for Fooling Deep Neural Networks
Su, J., Vargas, D. V., & Sakurai, K. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2890858 · Cited by 2,406 · see citing works
StarGAN v2: Diverse Image Synthesis for Multiple Domains
Choi, Y., Uh, Y., Yoo, J., & Ha, J.-W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00821 · Cited by 1,663 · see citing works
Training Generative Adversarial Networks with Limited Data
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., & Aila, T. (2020) · arXiv · doi:10.48550/arxiv.2006.06676 · Cited by 1,170 · see citing works
Deep Supervised Hashing for Fast Image Retrieval
Liu, H., Wang, R., Shan, S., & Chen, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.227 · Cited by 933 · see citing works
Deep hashing for compact binary codes learning
Liong, V. E., Lu, J., Wang, G., Moulin, P., & Zhou, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298862 · Cited by 545 · see citing works
BreCaHAD: a dataset for breast cancer histopathological annotation and diagnosis
Aksaç, A., Demetrick, D. J., Özyer, T., & Alhajj, R. (2019) · BMC Research Notes · doi:10.1186/s13104-019-4121-7 · Cited by 123 · see citing works
Adversarial Examples for Hamming Space Search
Yang, E., Liu, T., Deng, C. D., & Tao, D. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2882908 · Cited by 121 · see citing works
Targeted Attack for Deep Hashing Based Retrieval
Bai, J., Chen, B., Li, Y., Wu, D., Guo, W., Xia, S., & Yang, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58452-8_36 · Cited by 86 · see citing works
Deep Supervised Hashing for Multi-Label and Large-Scale Image Retrieval
Wu, D., Lin, Z., Li, B., Ye, M., & Wang, W. (2017) · International Conference on Multimedia Retrieval · doi:10.1145/3078971.3078989 · Cited by 66 · see citing works
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing
Wang, X., Zhang, Z., Wu, B., Shen, F., & Lu, G. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01609 · Cited by 57 · see citing works
It's Not What It Looks Like: Manipulating Perceptual Hashing based Applications
Hao, Q., Luo, L., Jan, S. T. K., & Wang, G. (2021) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3460120.3484559 · Cited by 37 · see citing works
Xiao, Y., & Wang, C. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00197 · Cited by 36 · see citing works
Evaluating robustness of perceptual image hashing algorithms
Drmic, A., Silic, M., Delac, G., Vladimir, K., & Kurdija, A. S. (2017) · 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) · doi:10.23919/mipro.2017.7973569 · Cited by 35 · see citing works
Targeted Attack and Defense for Deep Hashing
Wang, X., Zhang, Z., Lu, G., & Xu, Y. D. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3463233 · Cited by 26 · see citing works
Jain, S., Cretu, A.-M., & de Montjoye, Y.-A. (2021) · arXiv · doi:10.48550/arxiv.2106.09820 · Cited by 21 · cited 1× · see citing works
“Similar works investigated the robustness of non-deep perceptual hashing algorithms against adversarial attacks [24, 28] and their robustness [15] against visible image modifications.”
BackgroundRevHashNet: Perceptually de-hashing real-valued image hashes for similarity retrieval
Wang, Y., Palangi, H., Wang, Z. J., & Wang, H. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.06.018 · Cited by 13 · see citing works
Adversarial collision attacks on image hashing functions
Dolhansky, B., & Ferrer, C. C. (2020) · arXiv · doi:10.48550/arxiv.2011.09473 · Cited by 13 · see citing works
7 The United Kingdom Government
McFadden, J., & McFadzean, D. (2016) · Edinburgh University Press eBooks · doi:10.1515/9780748698318-010 · Cited by 6 · see citing works
Flagged first, then by citations
3 of the 36 references couldn’t be matched to a known paper.
Research works printed but not linked: 10
- [1][1] Hal Abelson, Ross Anderson, Steven M. Bellovin, Josh Benaloh, Matt Blaze, Jon Callas, Whitfield Diffie, Susan Landau, Peter G. Neumann, Ronald L. Rivest, Jeffrey I. Schiller, Bruce Schneier, Vanessa Teague, and Carmela Troncoso. Bugs in our pockets: The risks of client-side scanning. CoRR , abs/2110.07450, 2021. - · arXiv
- [13][13] Noam Eshed. Novelty detection and analysis in convolutional neural networks. Master's thesis, Cornell University, 2020. -
- [19][19] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In NeurIPS , volume 27, 2014. -
- [20][20] Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. In ICLR , 2015. -
- [31][31] Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Li Fei-Fei. Novel dataset for fine-grained image categorization. In First Workshop on Fine-Grained Visual Categorization, CVPR , 2011. -
- [39][39] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. In ICLR , 2018. -
- [41][41] Official Journal of the European Union. Regulation (EU) 2021/1232, 2021. https://eur-lex.europa. eu/legal-content/EN/TXT/?uri=CELEX: 32021R1232 , accessed: Nov. 16, 2021. -
- [43][43] Benny Pinkas. A review of the cryptography behind the apple psi system, 2021. https://www.apple.com/ child-safety/pdf/Technical\_Assessment\_ of\_CSAM\_Detection\_Benny\_Pinkas.pdf , accessed: Oct. 1, 2021. -
- [46][46] Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. Intriguing properties of neural networks. In ICLR , 2014. -
- [56][56] F. Zhao, Yongzhen Huang, Liang Wang, and Tieniu Tan. Deep semantic ranking based hashing for multi-label image retrieval. In CVPR , pages 1556-1564, 2015.
Cited by
Sorted by citations
Poisoning Web-Scale Training Datasets is Practical
Carlini, N., Jagielski, M., Choquette-Choo, C. A., Paleka, D., Pearce, W., Anderson, H., Terzis, A., Thomas, K., & Tramèr, F. (2024) · 2024 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp54263.2024.00179 · Cited by 138 · see citing works
Poisoning Web-Scale Training Datasets is Practical
Carlini, N., Jagielski, M., Choquette-Choo, C. A., Paleka, D., Pearce, W., Anderson, H., Terzis, A., Thomas, K., & Tramèr, F. (2023) · arXiv · doi:10.48550/arxiv.2302.10149 · Cited by 138 · see citing works
“Switching to a perceptual hash function (which aims for invariance to small image changes) would lead to higher utility, but would not meaningfully prevent our poisoning attacks because an attacker could upload poisoned images that were adversarially modified to fool the perceptual hash [26,29,68].”
BackgroundExploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Struppek, L., Hintersdorf, D., Friedrich, F., Br, M., Schramowski, P., & Kersting, K. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15388 · Cited by 48 · see citing works
Self-citationSoK: Content Moderation for End-to-End Encryption
Scheffler, S., & Mayer, J. R. (2023) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2023-0060 · Cited by 35 · see citing works
Hintersdorf, D., Struppek, L., Brack, M., Friedrich, F., Schramowski, P., & Kersting, K. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15461 · Cited by 18 · see citing works
Self-citationHamming distributions of popular perceptual hashing techniques
McKeown, S., & Buchanan, W. J. (2023) · Forensic Science International: Digital Investigation · doi:10.1016/j.fsidi.2023.301509 · Cited by 15 · see citing works
Discovering child sexual abuse material creators' behaviors and preferences on the dark web
Ngo, V. M., Gajula, R., Thorpe, C., & McKeever, S. (2023) · Child Abuse & Neglect · doi:10.1016/j.chiabu.2023.106558 · Cited by 14 · see citing works
Public Verification for Private Hash Matching
Scheffler, S., Kulshrestha, A., & Mayer, J. R. (2023) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46215.2023.10179349 · Cited by 14 · see citing works
Hintersdorf, D., Struppek, L., & Kersting, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73741-1_16 · Cited by 10 · see citing works
Self-citationCombining AI and AM – Improving approximate matching through transformer networks
Uhlig, F., Struppek, L., Hintersdorf, D., Göbel, T., Baier, H., & Kristian Kersting, B. (2023) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2023.301570 · Cited by 10 · see citing works
Self-citationGeierhaas, L., Otto, F., Häring, M., & Smith, M. (2023) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46215.2023.10179417 · Cited by 8 · see citing works
Jain, S., Creţu, A.-M., Cully, A., & de Montjoye, Y.-A. (2023) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46215.2023.10179310 · Cited by 8 · see citing works
Don’t Break the Chain: Measuring Message Forwarding on WhatsApp
Melo, P. D. F., Hoseini, M., Zannettou, S., & Benevenuto, F. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31372 · Cited by 7 · see citing works
Ngo, V. M., Dang, C. N., Thorpe, C., & McKeever, S. (2023) · Preprints.org · doi:10.20944/preprints202301.0046.v1 · Cited by 7 · see citing works
On the Robustness of Malware Detectors to Adversarial Samples
Salman, M., Zhao, B. Z. H., Asghar, H. J., Ikram, M., Kaushik, S., & Kâafar, M. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82362-6_10 · Cited by 6 · see citing works
Ngo, V. M., Thorpe, C., Dang, C. N., & McKeever, S. (2022) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf55975.2022.10013853 · Cited by 7 · see citing works
Bhardwaj, D., Guthoff, C., Dabrowski, A., Fahl, S., & Krombholz, K. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642310 · Cited by 5 · see citing works
ARIA: Adversarially Robust Image Attribution for Content Provenance
Andriushchenko, M., Li, X., Oxholm, G., Gittings, T., Bui, T., Flammarion, N., & Collomosse, J. P. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00013 · Cited by 5 · see citing works
Using Perceptual Hashing for Targeted Content Scanning
Twenning, L., Baier, H., & Göbel, T. (2023) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-42991-0_7 · Cited by 5 · see citing works
Distance distributions and runtime analysis of perceptual hashing algorithms
Sharma, S. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104310 · Cited by 4 · see citing works
Perceptual Hashing Algorithms for Image Recognition
Singh, A., Khan, M. Z., Sharma, S., & Debnath, N. C. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-81308-5_9 · Cited by 4 · see citing works
Perceptual Hash Inversion Attacks on Image-Based Sexual Abuse Removal Tools
Hawkes, S., Weinert, C., Almeida, T., & Mehrnezhad, M. (2024) · IEEE Security & Privacy · doi:10.1109/msec.2024.3485497 · Cited by 3 · see citing works
Beyond Hamming Distance: Exploring spatial encoding in perceptual hashes
McKeown, S. (2025) · Forensic Science International: Digital Investigation · doi:10.1016/j.fsidi.2025.301878 · Cited by 3 · see citing works
Merdian, H. L., Allardyce, S., Boeck, M. D., Gannon, C., Janssen, E., Klapilová, K., McCartan, K., von Franqué, F., & Lehmann, R. (2023) · Forensische Psychiatrie Psychologie Kriminologie · doi:10.1007/s11757-023-00796-2 · Cited by 3 · see citing works
Alkhowaiter, M., Almubarak, K., Alyami, M., Alghamdi, A. M., & Zou, C. C. (2022) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom55135.2022.10017725 · Cited by 3 · see citing works
On a global child protection fund financed by international tech companies
Açar, K. V. (2022) · Global Policy · doi:10.1111/1758-5899.13146 · Cited by 2 · see citing works
Experimental Analyses of the Physical Surveillance Risks in Client-Side Content Scanning
Hooda, A., Labunets, A., Kohno, T., & Fernandes, E. (2024) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2024.241401 · Cited by 2 · see citing works
Ali, K. A. R., & Somu, C. S. (2025) · International Conference on Intelligent Computing and Robotics (ICICR) · doi:10.1109/icicr65456.2025.00087 · Cited by 2 · see citing works
CAMVA: An Extension Architecture of CNN Accelerators for Multi-View Acceleration
Chen, J., Ding, Y., Liu, C., & Li, K. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3624213 · Cited by 2 · see citing works
Staat und Staatlichkeit im digitalen Zeitalter
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657 · Cited by 2 · see citing works
Generative Collision Attack on Deep Image Hashing
Ying, L., Xiong, C., Qin, C., Luo, X., Qian, Z., & Zhang, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3547566 · Cited by 2 · see citing works
Coelho, T., Ribeiro, L. S. F., Macedo, J. I., dos Santos, J. A., & Avila, S. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732102 · Cited by 2 · see citing works
Twenning, L., & Baier, H. (2024) · European Interdisciplinary Cybersecurity Conference (EICC) · doi:10.1145/3655693.3655712 · Cited by 1 · see citing works
Geierhaas, L., Martius, F., Arumugam, A., & Smith, M. X. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00086 · Cited by 1 · see citing works
Clean Image May Be Dangerous: Data Poisoning Attacks Against Deep Hashing
Li, S., Zhang, J., Qi, Y., Chen, K., Zhang, T., Zhang, W., & Yu, N. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3607774 · Cited by 1 · see citing works
Robustness and Collision-Resistance of PhotoDNA
Steinebach, M. (2024) · Journal of Cyber Security and Mobility · doi:10.13052/jcsm2245-1439.1339 · Cited by 1 · see citing works
TripletViNet: Mitigating Misinformation Video Spread Across Platforms
Smolovic, P., Dahanayaka, T., & Thilakarathna, K. (2024) · doi:10.1145/3660512.3665519 · Cited by 1 · see citing works
Umgang mit GenAI und Deepfakes
Steinebach, M. (2024) · Datenschutz und Datensicherheit - DuD · doi:10.1007/s11623-024-2005-z · Cited by 1 · see citing works
Jiang, N., Sun, B., Kim, N., Sim, T., & Han, J. (2026) · 2026 IEEE Symposium on Security and Privacy Workshops (SPW) · doi:10.1109/spw72489.2026.00029
Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks
Madden, J., Bhavsar, M., Dorje, L., & Li, X. (2024) · arXiv · doi:10.48550/arxiv.2406.00918
“Surprisingly, the newest edition of NeuralHash that we experimented with was still not robust to filtering, rotating, and mirroring, similar to the first edition experimented in [11][16].”
InfluentialGreef, S. (2023) · transcript Verlag eBooks · doi:10.1515/9783839470657-094
IV.2.2 Modell der Staatlichkeit: Interventionsstaat
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-053
IV.2.1 Modell des Staates: Leistungsstaat
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-052
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-054
IV.1.2 Modelle der Staatlichkeit in der Steuerungsdimension
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-050
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-051
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-055
IV.3.2 Modell der Staatlichkeit: Kooperativer Staat
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-057
IV.3.1 Modell des Staates: Gewährleistungsstaat
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-056
V.3.7 Politics III: Governance of Algorithms – Regulierung von Algorithmen
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-082
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-083
V.3.6 Policy III: Digital Services Act (DSA)
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-081
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-084
I.3.2 Methodik und Fallauswahl
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-012
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-013
I.2.3 Kontingenz von Steuerung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-009
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-008
I.3.1 Fragestellung und forschungsleitende Hypothesen
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-011
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-014
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-015
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-010
V.1.3 Policy: Digitale Gesundheitsinfrastruktur und Versorgungsangebote
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-068
III.2.6 Selbst- und Ko-Regulierung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-045
II.2.9 Von den transformativen Herausforderungen zur Steuerung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-027
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-toc
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-007
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-043
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-089
III.2.7 Information und Überzeugung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-046
II.3.2 Polity I: Steuerungssubjekt – Institutionen, Behörden und Zuständigkeiten
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-030
VI.1.2 Veränderte Steuerungsformen?
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-086
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-002
V.3.2 Polity: Akteure und Akteurskonstellationen
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-077
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-004
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-034
VI.1.1 Neue digitale Steuerungsinstrumente?
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-085
IV.1.1 Modelle des Staates in der Leistungsdimension
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-049
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-097
III.1.3 Netzwerk: Horizontale Steuerung (Governance)
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-037
II.2.8 Komplexität, Wicked Problems, Ambiguität und Kontingenz
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-026
V.1.2 Politics I: Steuerungsparadigma im Wandel
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-067
II.2.3 Fake News und Desinformation
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-021
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-042
V.2.3 Politics I: Bündnisse und Dialogorientierung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-073
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-040
II.2.7 Entgrenzung und Schrumpfung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-025
I.1.2 Transformation von Staatlichkeit und Staat im Wandel
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-005
VI.1.3 Das neue Staatsbild des kontingenten Patchworkstaates
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-087
III.1.4 Korporatismus: Selbstorganisation (Ko-Regulierung)
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-038
II.3.4 Politics: Moderation und Verhandlung mit unklaren Kompetenzen
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-032
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-039
II.2.5 Datafizierung, Algorithmizität und Künstliche Intelligenz
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-023
V.2.1 Policy: Industrie 4.0 – 4. Industrielle Revolution, oder: Das neue Maschinenzeitalter
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-071
V.3.1 Policy I: Netzwerkdurchsetzungsgesetz (NetzDG)
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-076
V.3.5 Politics II: Privatisierung der Rechtsetzung
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-080
IV.3.4 Der Wandel der Modelle vom Modernen Staat I zu II
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-059
III.1.2 Markt: Selbststeuerung (Regulierung)
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-036
II.3.1 Policy: Die vier Dimensionen der Digitalpolitik
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-029
V.1.4 Politics II: Neue digitale Steuerungsinstrumente in der Coronakrise?
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-069
IV.4.2 Utopischer Mikro-Steuerungsstaat
Greef, S. (2023) · Politik in der digitalen Gesellschaft · doi:10.14361/9783839470657-062
- Authors
- Struppek, L., Hintersdorf, D., Neider, D., & Kersting, K.
- Affiliations
- Technische Universität Darmstadt (DE)
- Carl von Ossietzky Universität Oldenburg (DE)
- Department of Computer Science and Centre for Cognitive Science, Technical University of Darmstadt, Germany and Hessian Center for Artificial Intelligence, Germany
- Venue
- 2022 ACM Conference on Fairness Accountability and Transparency
- Publisher
- ACM
- Published
- 2022-06-20
- Pages
- 58-69
- OpenAlex
- W3214430180
- Cited by
- 153
- References
- 36
- Citations by year
- 2026: 12 · 2025: 11 · 2024: 14 · 2023: 112 · 2022: 4
- FWCI
- 12.78
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion, cc-by-sa)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Bundesministerium für Bildung und Forschung (13N15343)
- National Research Center for Applied Cybersecurity ATHENE
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- hash collision attacks, adversarial attacks, privacy, iCloud, image editing, hash robustness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
