mlsanityData to 7 Oct 2026

RiDDLE: Reversible and Diversified De-identification with Latent Encryptor

arXiv 2303.05171 ↗First posted 9 Mar 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused. Built upon a pre-learned StyleGAN2 generator, RiDDLE manages to encrypt and decrypt the facial identity within the latent space. The design of RiDDLE has three appealing properties. First, the encryption process is cipher-guided and hence allows diverse anonymization using different passwords. Second, the true identity can only be decrypted with the correct password, otherwise the system will produce another de-identified face to maintain the privacy. Third, both encryption and decryption share an efficient implementation, benefiting from a carefully tailored lightweight encryptor. Comparisons with existing alternatives confirm that our approach accomplishes the de-identification task with better quality, higher diversity, and stronger reversibility. We further demonstrate the effectiveness of RiDDLE in anonymizing videos. Code and models will be made publicly available.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

22 of 28 references.

References · 22

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  6. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  7. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  8. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  9. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  10. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  11. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  12. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
10 more
  1. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  2. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  3. 2020CIAGAN: Conditional Identity Anonymization Generative Adversarial Networkscited by 88
  4. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  5. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  6. 2019Live Face De-Identification in Videocited by 48
  7. 2018A Hybrid Model for Identity Obfuscation by Face Replacementcited by 43
  8. 2019Password-conditioned Anonymization and Deanonymization with Face Identity Transformerscited by 24
  9. 2018Privacy-Protective-GAN for Face De-identificationcited by 14
  10. 2022Contrastive Learning for Diverse Disentangled Foreground Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 7; 2026: 4.

21 papers.

Sort:

By area:

  1. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  2. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  3. 2024G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priorscited by 20
  4. 2024Face Anonymization Made Simplecited by 18
  5. 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
  6. 2024Medical Manifestation-Aware De-Identificationcited by 4
  7. 2025NullFace: Training-Free Localized Face Anonymizationcited by 4
  8. 2024SemDP: Semantic-level Differential Privacy Protection for Face Datasetscited by 1
  9. 2025FaceAnonyMixer: Cancelable Faces via Identity Consistent Latent Space Mixingcited by 1
  10. 2025ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizercited by 1
  11. 2025Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymizationcited by 1
  12. 2025Reverse Personalizationcited by 1
9 more
  1. 2023PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flowcited by 0
  2. 2023Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identificationcited by 0
  3. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  4. 2025Secure and reversible face anonymization with diffusion modelscited by 0
  5. 2025FLUID: Training-Free Face De-identification via Latent Identity Substitutioncited by 0
  6. 2026SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacycited by 0
  7. 2026Face anonymization preserving facial expressions and photometric realismcited by 0
  8. 2026Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMscited by 0
  9. 2026HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approachcited by 0