virtual u defeating face liveness detection by
play

Virtual U: Defeating Face Liveness Detection by Building Virtual - PowerPoint PPT Presentation

Virtual U: Defeating Face Liveness Detection by Building Virtual Models From Your Public Photos Yi Xu, True Price, Jan-Michael Frahm, and Fabian Monrose Department of Computer Science, University of North Carolina at Chapel Hill USENIX Security


  1. Virtual U: Defeating Face Liveness Detection by Building Virtual Models From Your Public Photos Yi Xu, True Price, Jan-Michael Frahm, and Fabian Monrose Department of Computer Science, University of North Carolina at Chapel Hill USENIX Security August 11, 2016

  2. Face Authentication: Convenient Security image source

  3. Evolution of Adversarial Models  Attack: Still-image Spoofing

  4. Evolution of Adversarial Models  Attack: Still-image Spoofing  Defense: Liveness Detection

  5. Evolution of Adversarial Models  Attack: Still-image Spoofing  Defense: Liveness Detection  Attack:Video Spoofing

  6. Evolution of Adversarial Models  Attack: Still-image Spoofing  Defense: Liveness Detection  Attack:Video Spoofing  Defense: Motion Consistency

  7. Evolution of Adversarial Models  Attack: Still-image Spoofing  Defense: Liveness Detection  Attack:Video Spoofing  Defense: Motion Consistency  Attack: 3D-Printed Masks

  8. Virtual U: A New Attack We introduce a new VR-based attack on face authentication systems solely using publicly available photos of the victim

  9. Virtual U: A New Attack ❶ ❷ ❸ ❹ Input Landmark 3D Model Image-based Gaze Web Photos Extraction Reconstruction Texturing Correction ❺ ❻ Viewing with Virtual Reality System Expression Animation

  10. Leveraging Social Media

  11. Landmark Extraction

  12. 3D Face Model (e.g., thin-to-heavyset) Variation Identity Expression Variation (e.g., frowning-to-smiling)

  13. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model 𝐵 𝑓𝑦𝑞 (e.g., thin-to-heavyset) 𝑇 Variation Identity 𝐵 𝑗𝑒 Expression Variation (e.g., frowning-to-smiling)

  14. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model 𝑇 Reprojection

  15. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model Pose 𝛽 𝑗𝑒 𝛽 𝑓𝑦𝑞

  16. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model Pose 𝛽 𝑗𝑒 𝛽 𝑓𝑦𝑞

  17. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model Pose 𝛽 𝑗𝑒 𝛽 𝑓𝑦𝑞

  18. 3D Face Model

  19. 3D Face Model

  20. 3D Face Model

  21. 3D Face Model Pose Pose 𝛽 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝛽 𝑗𝑒 Pose Pose 𝛽 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞

  22. Multi-Image Modeling Single image Multiple images

  23. Texturing Direct T exturing 2D Poisson Editing

  24. Texturing Direct T exturing 2D Poisson Editing 3D Poisson Editing

  25. Gaze Correction R R B B G G

  26. Gaze Correction

  27. Virtual U: A New Attack ❶ ❷ ❸ ❹ Input Landmark 3D Model Image-based Gaze Web Photos Extraction Reconstruction Texturing Correction ❺ ❻ Viewing with Virtual Reality System Expression Animation

  28. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = Expression Animation Smiling Laughing Blinking Raising Eyebrows

  29. VR Display Printed Marker VR System Authentication Device

  30. VR Display

  31. Experiments * KeyLemon Interaction-based liveness detection Mobius Motion-based * TrueKey liveness detection BioID Texture-based liveness detection 1 U

  32. Experiments  20 participants  Aged 24 to 44  14 males, 6 females  Various ethnicities  Two tests  Indoor photo of the subject in the same environment as registration  Publicly accessible photos  Anywhere from 3 to 27 photos per person  Low-, medium-, and high-quality  Potentially strong changes in appearance over time

  33. Experiments Indoor Image Online Avg. #Tries (Single frontal image) KeyLemon 100% 85% 1.6 Mobius 100% 80% 1.5 TrueKey 100% 70% 1.3 BioID 100% 55% 1.7 100% 0% -- 1 U

  34. Observations  Medium- and high-resolution photos work best  Photos from professional photographers (weddings, etc.) Group photos provide consistent frontal views   Often lower resolution Only a small number of photos required   One or two forward-facing photos  One or two higher-resolution photos

  35. Experiments How does resolution affect reconstruction quality?

  36. Experiments How does rotation affect reconstruction quality?

  37. Experiments Combining high-res rotation with low-res front-facing? +

  38. Experiments  Virtual U is successful against liveness detection

  39. Experiments  Virtual U is successful against liveness detection  Also successful against motion consistency

  40. Experiments  “Seeing Your Face is Not Enough: An Inertial Sensor-Based Liveness Detection for Face Authentication” (Li et al., ACM CCS’15)  Device motion measured by inertial sensor data  Head pose estimated from input video  Train a classifier to identify real data (correlated signals) versus spoofed video data

  41. Experiments T est Result (Accept Rate) Training Data (Pos. Data vs. Neg. Data) VR Spoof Real Face Video Spoof 98.0% 1.0% 99.5% Real vs. Video

  42. Experiments T est Result (Accept Rate) Training Data (Pos. Data vs. Neg. Data) VR Spoof Real Face Video Spoof 98.0% 1.0% 99.5% Real vs. Video 67.0% 0.0% 50.0% Real vs. Video +VR

  43. Experiments T est Result (Accept Rate) Training Data (Pos. Data vs. Neg. Data) VR Spoof Real Face Video Spoof 98.0% 1.0% 99.5% Real vs. Video 67.0% 0.0% 50.0% Real vs. Video +VR Real vs. VR 67.0% - 51.0%

  44. Mitigations  Alternative/additional hardware  Infrared imaging (e.g. Windows Hello)  Random structured light projection image source

  45. Mitigations  Alternative/additional hardware  Infrared imaging (e.g. Windows Hello)  Random structured light projection  Improved defense against low-resolution synthetic textures Original Downsized to 50px

  46. Conclusion  We introduce a new VR-based attack on face authentication systems solely using publicly available photos of the victim  This attack bypasses existing defenses of liveness detection and motion consistency  At a minimum, face authentication software must improve against VR- based attacks with low-resolution textures  The increasing ubiquity of VR will continue to challenge computer- vision-based authentication systems

  47. Thank you! Questions?

  48. Overview  Face Authentication  Virtual U: A VR-based attack  Evaluation  Mitigations  Conclusion

  49. Evolution of Adversarial Models  Attack: Still-image Spoofing  Defense: Liveness Detection  Attack:Video Spoofing  Defense: Motion Consistency  Attack: 3D-Printed Masks  Defense: Texture Detection

  50. 3D Face Model (e.g., thin-to-heavyset) Variation Identity Expression Variation (e.g., frowning-to-smiling)

  51. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model 𝐵 𝑓𝑦𝑞 (e.g., thin-to-heavyset) 𝑇 Variation Identity 𝐵 𝑗𝑒 Expression Variation (e.g., frowning-to-smiling)

  52. 𝑇 + 𝐵 𝑗𝑒 𝛽 𝑗𝑒 + 𝐵 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 𝑇 = 3D Face Model 𝑇 Reprojection 2 + 𝛾 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 2 2 + 𝛾 𝑗𝑒 𝛽 𝑗𝑒 𝑄,𝛽 𝑗𝑒 ,𝛽 𝑓𝑦𝑞 min 𝑡 𝑗 − 𝑄𝑇 𝑗 𝑗 Normalization Pose Summed over all landmarks

  53. 3D Face Model

  54. Multi-Image Modeling Single Image 2 + 𝛾 𝑓𝑦𝑞 𝛽 𝑓𝑦𝑞 2 2 + 𝛾 𝑗𝑒 𝛽 𝑗𝑒 𝑄,𝛽 𝑗𝑒 ,𝛽 𝑓𝑦𝑞 min 𝑡 𝑗 − 𝑄𝑇 𝑗 𝑗 Multiple Images 2 + 𝛾 𝑓𝑦𝑞 2 2 + 𝛾 𝑗𝑒 𝛽 𝑗𝑒 𝑓𝑦𝑞 𝑄,𝛽 𝑗𝑒 ,𝛽 𝑓𝑦𝑞 min 𝑡 𝑛𝑗 − 𝑄 𝑛 𝑇 𝑛𝑗 𝛽 𝑛 𝑛 𝑗 𝑛 Sum over all images

  55. Multi-Image Modeling Corners of the eyes and mouth are stable landmarks Contour points are variable landmarks

  56. Multi-Image Modeling Multiple Images 2 + 𝑜𝑝𝑠𝑛. 𝑄,𝛽 𝑗𝑒 ,𝛽 𝑓𝑦𝑞 min 𝑡 𝑛𝑗 − 𝑄 𝑛 𝑇 𝑛𝑗 𝑛 𝑗 Multiple Images with Landmark Weighting 1 2 + 𝑜𝑝𝑠𝑛. 𝑄,𝛽 𝑗𝑒 ,𝛽 𝑓𝑦𝑞 min 𝑡 2 𝑡 𝑛𝑗 − 𝑄 𝑛 𝑇 𝑛𝑗 𝜏 𝑗 𝑛 𝑗 Higher weighting for stable landmarks

  57. Experiments  20 participants  Aged 24 to 44  14 males, 6 females  Various ethnicities  Two tests  Indoor photo of the subject in the same environment as registration  Publicly accessible photos  Anywhere from 3 to 27 photos per person  Low-, medium-, and high-quality  Potentially strong changes in appearance over time

  58. Experiments How does rotation affect reconstruction quality? 20 30 40 20 30 40

  59. Experiments VR System Google Cardboard Authentication Device

Recommend


More recommend