Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
117 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks (2410.18687v1)

Published 24 Oct 2024 in cs.CV

Abstract: Despite significant advances in deepfake detection, handling varying image quality, especially due to different compressions on online social networks (OSNs), remains challenging. Current methods succeed by leveraging correlations between paired images, whether raw or compressed. However, in open-world scenarios, paired data is scarce, with compressed images readily available but corresponding raw versions difficult to obtain. This imbalance, where unpaired data vastly outnumbers paired data, often leads to reduced detection performance, as existing methods struggle without corresponding raw images. To overcome this issue, we propose a novel approach named the open-world deepfake detection network (ODDN), which comprises two core modules: open-world data aggregation (ODA) and compression-discard gradient correction (CGC). ODA effectively aggregates correlations between compressed and raw samples through both fine-grained and coarse-grained analyses for paired and unpaired data, respectively. CGC incorporates a compression-discard gradient correction to further enhance performance across diverse compression methods in OSN. This technique optimizes the training gradient to ensure the model remains insensitive to compression variations. Extensive experiments conducted on 17 popular deepfake datasets demonstrate the superiority of the ODDN over SOTA baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Mesonet: a compact facial video forgery detection network. In 2018 IEEE international workshop on information forensics and security (WIFS), 1–7. IEEE.
  2. Reverse engineering of generative models: Inferring model hyperparameters from generated images. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  3. Cao, J.; et al. 2022. End-to-end reconstruction-classification learning for face forgery detection. In CVPR, 4113–4122.
  4. Chen, L.; et al. 2022. Self-supervised learning of adversarial example: Towards good generalizations for deepfake detection. In CVPR, 18710–18719.
  5. TMG-GAN: Generative Adversarial Networks-Based Imbalanced Learning for Network Intrusion Detection. IEEE Transactions on Information Forensics and Security, 19: 1156–1167.
  6. Fourier spectrum discrepancies in deep network generated images. Advances in neural information processing systems, 33: 3022–3032.
  7. He, Y.; et al. 2021. Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, 2534–2541. International Joint Conferences on Artificial Intelligence Organization.
  8. Jeong, Y.; et al. 2022a. BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection. In WACV, 48–57.
  9. Jeong, Y.; et al. 2022b. FingerprintNet: Synthesized Fingerprints for Generated Image Detection. In ECCV, 76–94. Springer.
  10. Jeong, Y.; et al. 2022c. FrePGAN: robust deepfake detection using frequency-level perturbations. In AAAI, volume 36, 1060–1068.
  11. Ju, Y.; et al. 2022. Fusing Global and Local Features for Generalized AI-Synthesized Image Detection. In 2022 IEEE International Conference on Image Processing (ICIP), 3465–3469. IEEE.
  12. Adam: A Method for Stochastic Optimization. In ICLR (Poster).
  13. Quality-agnostic deepfake detection with intra-model collaborative learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 22378–22389.
  14. Gradient alignment for cross-domain face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 188–199.
  15. Generating Robust Adversarial Examples against Online Social Networks (OSNs). ACM Transactions on Multimedia Computing, Communications and Applications, 20(4): 1–26.
  16. Ojha, U.; et al. 2023. Towards universal fake image detectors that generalize across generative models. In CVPR, 24480–24489.
  17. Thinking in frequency: Face forgery detection by mining frequency-aware clues. In European conference on computer vision, 86–103. Springer.
  18. Faceforensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF international conference on computer vision, 1–11.
  19. Detecting deepfakes with self-blended images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18720–18729.
  20. Optimal pre-filtering for improving Facebook shared images. IEEE Transactions on Image Processing, 30: 6292–6306.
  21. Robust high-capacity watermarking over online social network shared images. IEEE Transactions on Circuits and Systems for Video Technology, 31(3): 1208–1221.
  22. Processing-aware privacy-preserving photo sharing over online social networks. In Proceedings of the 24th ACM international conference on Multimedia, 581–585.
  23. GANGen-Detection: A Dataset generated by GANs for Generalizable deepfake Detection. https://github.com/chuangchuangtan/GANGen-Detection.
  24. Tan, C.; et al. 2023. Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection. In CVPR (CVPR), 12105–12114.
  25. Visualizing data using t-SNE. Journal of machine learning research, 9(11).
  26. Bagm: A backdoor attack for manipulating text-to-image generative models. IEEE Transactions on Information Forensics and Security.
  27. Wang, C.; et al. 2021. Representative forgery mining for fake face detection. In CVPR, 14923–14932.
  28. Wang, S.-Y.; et al. 2020. CNN-generated images are surprisingly easy to spot… for now. In CVPR, 8695–8704.
  29. AltFreezing for More General Video Face Forgery Detection. In CVPR, 4129–4138.
  30. Wang, Z.; et al. 2023b. DIRE for Diffusion-Generated Image Detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 22445–22455.
  31. Woo, S.; et al. 2022. Add: Frequency attention and multi-view based knowledge distillation to detect low-quality compressed deepfake images. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 122–130.
  32. Robust image forgery detection against transmission over online social networks. IEEE Transactions on Information Forensics and Security, 17: 443–456.
  33. Robust Camera Model Identification over Online Social Network Shared Images via Multi-Scenario Learning. IEEE Transactions on Information Forensics and Security.
  34. Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems, 33: 5824–5836.
  35. Reinforcement learning solution for cyber-physical systems security against replay attacks. IEEE Transactions on Information Forensics and Security.
  36. Towards Secure and Robust Steganography for Black-box Generated Images. IEEE Transactions on Information Forensics and Security.
  37. Encrypted and compressed key-value store with pattern-analysis security in cloud systems. IEEE Transactions on Information Forensics and Security.
  38. DIBAD: A Disentangled Information Bottleneck Adversarial Defense Method using Hilbert-Schmidt Independence Criterion for Spectrum Security. IEEE Transactions on Information Forensics and Security.
  39. ISTVT: interpretable spatial-temporal video transformer for deepfake detection. IEEE Transactions on Information Forensics and Security, 18: 1335–1348.
  40. Multi-attentional deepfake detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2185–2194.
  41. Generative steganography via auto-generation of semantic object contours. IEEE Transactions on Information Forensics and Security.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets