mlsanityData to 14 Oct 2026

Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration

arXiv 2309.01582 ↗First posted 4 Sep 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial face examples possess two critical properties: Visual Quality and Transferability. However, existing approaches rarely address these properties simultaneously, leading to subpar results. To address this issue, we propose a novel adversarial attack technique known as Adversarial Restoration (AdvRestore), which enhances both visual quality and transferability of adversarial face examples by leveraging a face restoration prior. In our approach, we initially train a Restoration Latent Diffusion Model (RLDM) designed for face restoration. Subsequently, we employ the inference process of RLDM to generate adversarial face examples. The adversarial perturbations are applied to the intermediate features of RLDM. Additionally, by treating RLDM face restoration as a sibling task, the transferability of the generated adversarial face examples is further improved. Our experimental results validate the effectiveness of the proposed attack method.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

19 of 22 references.

References · 19

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  6. 2022Diffusion Models for Adversarial Purificationcited by 476
  7. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  8. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
  9. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 321
  10. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  11. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  12. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 97
7 more
  1. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 94
  2. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 80
  3. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 78
  4. 2020Towards Face Encryption by Generating Adversarial Identity Maskscited by 63
  5. 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognitioncited by 34
  6. 2019Adversarial Learning with Margin-based Triplet Embedding Regularizationcited by 29
  7. 2022Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 0; 2026: 2.

5 papers.

  1. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 8
  2. 2024Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Modelscited by 4
  3. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 4
  4. 2026A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Modelscited by 0
  5. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
  2. 2024OSDFace: One-Step Diffusion Model for Face Restoration
  3. 2025Gradient-Free Adversarial Purification with Diffusion Models
  4. 2026Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks
  5. 2025SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
  6. 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
  7. 2026Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
  8. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models