mlsanityData to 7 Oct 2026

SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy

arXiv 2602.04994 ↗First posted 4 Feb 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

With the deep integration of facial recognition into online banking, identity verification, and other networked services, achieving effective decoupling of identity information from visual representations during image storage and transmission has become a critical challenge for privacy protection. To address this issue, we propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection. SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component. By leveraging semantic-guided recomposition in the latent space of a diffusion model, it generates visually anonymous adversarial faces while maintaining machine-level identity consistency. The framework incorporates momentum-driven unrestricted perturbation optimization and a semantic-visual balancing factor to synthesize multiple visually diverse, highly natural adversarial samples. Furthermore, for authorized access, the protected image can be restored to its original form when the correct password is provided. Extensive experiments on the CelebA-HQ and FFHQ datasets demonstrate that SIDeR achieves a 99% attack success rate in black-box scenarios and outperforms baseline methods by 41.28% in PSNR-based restoration quality.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

44 of 63 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  11. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  12. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
32 more
  1. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  2. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 95
  3. 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunitiescited by 89
  4. 2020CIAGAN: Conditional Identity Anonymization Generative Adversarial Networkscited by 88
  5. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 77
  6. 2020Towards Face Encryption by Generating Adversarial Identity Maskscited by 62
  7. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  8. 2023CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Searchcited by 42
  9. 2023DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protectioncited by 34
  10. 2023Optimal Resource Allocation for U-Shaped Parallel Split Learningcited by 33
  11. 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protectioncited by 31
  12. 2024Transferable Adversarial Facial Images for Privacy Protectioncited by 26
  13. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  14. 2019Password-conditioned Anonymization and Deanonymization with Face Identity Transformerscited by 24
  15. 2025LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networkscited by 22
  16. 2023RiDDLE: Reversible and Diversified De-identification with Latent Encryptorcited by 21
  17. 2023Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Modelcited by 21
  18. 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
  19. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  20. 2025Constructing 4D Radio Map in LEO Satellite Networks with Limited Samplescited by 13
  21. 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attackscited by 13
  22. 2024LEO Satellite Networks Assisted Geo-distributed Data Processingcited by 10
  23. 2024Personalized Privacy Protection Mask Against Unauthorized Facial Recognitioncited by 10
  24. 2025Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoringcited by 10
  25. 2022Hiding Visual Information via Obfuscating Adversarial Perturbationscited by 7
  26. 2024Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priorscited by 7
  27. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  28. 2025SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compressioncited by 6
  29. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learningcited by 6
  30. 2025RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computingcited by 5
  31. 2025Optimizing Split Federated Learning with Unstable Client Participationcited by 5
  32. 2025Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection
  2. 2023Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework
  3. 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
  4. 2024Identity-Focused Inference and Extraction Attacks on Diffusion Models
  5. 2025Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization
  6. 2023Disguise without Disruption: Utility-Preserving Face De-Identification
  7. 2026DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition
  8. 2025MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models