mlsanityData to 14 Oct 2026

MS-GAGA: Metric-Selective Guided Adversarial Generation Attack

arXiv 2510.12468 ↗First posted 14 Oct 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a dual-stream attack module generates adversarial candidates: MNTD-PGD applies enhanced gradient calculations optimized for small perturbation budgets, while SG-PGD focuses perturbations on visually salient regions. This complementary design expands the adversarial search space and improves transferability across unseen models. In Stage 2, a metric-aware selection module evaluates candidates based on both their success against black-box models and their structural similarity (SSIM) to the original image. By jointly optimizing transferability and imperceptibility, MS-GAGA achieves up to 27% higher misclassification rates on unseen detectors compared to state-of-the-art attacks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

35 of 46 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2016Densely Connected Convolutional Networkscited by 6,720
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  10. 2013Intriguing properties of neural networkscited by 5,155
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
23 more
  1. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  2. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  3. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  4. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  5. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
  6. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  7. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  8. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
  9. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  10. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  11. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  12. 2018Noiseprint: a CNN-based camera model fingerprintcited by 114
  13. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  14. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  15. 2020Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examplescited by 66
  16. 2020DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythmscited by 65
  17. 2020Adversarial Threats to DeepFake Detection: A Practical Perspectivecited by 48
  18. 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
  19. 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
  20. 2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
  21. 2024DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusioncited by 29
  22. 2023Text-image guided Diffusion Model for generating Deepfake celebrity interactionscited by 8
  23. 2020GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systemscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attackscited by 1
  2. 2026Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidancecited by 1
  3. 2026ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectorscited by 0