mlsanityData to 7 Oct 2026

Differentially Private Imaging via Latent Space Manipulation

arXiv 2103.05472 ↗First posted 8 Mar 2021cs.CV cs.CRcited by 13

Not on the map. Why?

Abstract (arXiv)

There is growing concern about image privacy due to the popularity of social media and photo devices, along with increasing use of face recognition systems. However, established image de-identification techniques are either too subject to re-identification, produce photos that are insufficiently realistic, or both. To tackle this, we present a novel approach for image obfuscation by manipulating latent spaces of an unconditionally trained generative model that is able to synthesize photo-realistic facial images of high resolution. This manipulation is done in a way that satisfies the formal privacy standard of local differential privacy. To our knowledge, this is the first approach to image privacy that satisfies varepsilon-differential privacy for the person.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

22 of 36 references.

References · 22

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  8. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  9. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  10. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  11. 2017Machine Learning Models that Remember Too Muchcited by 165
  12. 2017Optimizing the Latent Space of Generative Networkscited by 157
10 more
  1. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  2. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  3. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  4. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  5. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  6. 2019AnonymousNet: Natural Face De-Identification with Measurable Privacycited by 50
  7. 2016Defeating Image Obfuscation with Deep Learningcited by 43
  8. 2018A Hybrid Model for Identity Obfuscation by Face Replacementcited by 43
  9. 2017Differentially Private Mixture of Generative Neural Networkscited by 39
  10. 2018Privacy-Protective-GAN for Face De-identificationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 3; 2024: 3; 2025: 2; 2026: 1.

13 papers.

Sort:

  1. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  2. 2022Sentence-level Privacy for Document Embeddingscited by 15
  3. 2021DeepBlur: A Simple and Effective Method for Natural Image Obfuscationcited by 13
  4. 2024A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directionscited by 10
  5. 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
  6. 2022Local Differential Privacy Image Generation Using Flow-based Deep Generative Modelscited by 5
  7. 2024PrivateGaze: Preserving User Privacy in Black-box Mobile Gaze Tracking Servicescited by 4
  8. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  9. 2026LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicingcited by 2
  10. 2024SemDP: Semantic-level Differential Privacy Protection for Face Datasetscited by 1
  11. 2022Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inversecited by 0
  12. 2023Differentially Private Cross-camera Person Re-identificationcited by 0
1 more
  1. 2025Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Taskscited by 0