Evaluation of Privacy Protection Performance of De-id Faces STSM - - PowerPoint PPT Presentation

Evaluation of Privacy Protection Performance of De-id Faces

STSM Report by Zongji Sun University of Hertfordshire, UK Host institution: Department of Electronic System, Aalborg University, Denmark

1

Aim of this STSM

• Evaluation of the UH face de-identification method

using the AAU face recognition system.

• UH face de-identification: k-Diff-furthest
• Methods in AAU face recognition system:
• LBP
• LPQ
• HOG
• Face datasets used in the evaluation
• FERET
• Multi-PIE

2

Our k-Diff-furthest method

Face features in a simplified 2D illustration

3 05/11/2015

k-Diff-furthest de-identified faces

• Original faces
• De-identified faces

4 05/11/2015

Re-identification risk of de-identified faces against their original faces

5 05/11/2015

Types of re-identification attacks

6

Gallery Probe Naïve recognition Original De-identified Reverse recognition De-identified Original Parrot recognition De-identified Mock De- identified

Performance of Threshold method

7 [1] Newton, E. M., Sweeney, L., & Malin, B. (2005). Preserving privacy by de-identifying face images. IEEE Transactions on Knowledge and Data Engineering, 17(2), 232–243. doi:10.1109/TKDE.2005.32

Face datasets - FERET

• 963 subjects each with

two face images captured at the same shooting session

• Nearly identical head

pose, hair details, upper body, clothing and background

• Details within face

region (e.g. facial expression) may be different

8

id: 002 id: 0043 id: 194

Face datasets – Multi-PIE

• 224 subjects each with

two face images captured at the same shooting session

• Nearly identical head

pose, hair details, upper body, clothing and background

• Details within face

region are different –

• ne neutral and the
• ther happy

9

id: 001 id: 002 id: 040

Examples of de-identified faces

Original De-id face without BG De-id face with BG

10

Re-identification Test

id: 00043 id: 00050 id: 00048 id: 00130 id: 00155 Original fa Original fb De-id fb

11

Re-identification Test

12

Without background Without background Without background 200200 Original fa Original fb De-id fb

200 x 200 Without background Orig De-id PCA + K-NN (Euclidean distance) 47.25% 0.10% LBP + K-NN (Euclidean distance) 74.25% 0.21% HOG + K-NN (Cosine distance) 47.14% 0.10% LPQ + K-NN (Cosine distance) 51.92% 0.21% LPQ + SVM 48.39% 0.21%

Re-identification Test (cont.)

13

Without background Without background Without background 300300 Original fa Original fb De-id fb FERET dataset 300 x 300 Without background Orig De-id PCA + k-NN (Euclidean distance) 42.37% 0% LBP + k-NN (Euclidean distance) 63.03% 0.21% HOG + k-NN (Cosine distance) 18.38% 0% LPQ + k-NN (Cosine distance) 45.79% 0.21% Multi-PIE dataset 300 x 300 Without background Orig De-id LBP + k-NN (Euclidean distance) 76.79% 0.45% LPQ + k-NN (Cosine distance) 61.16% 0%

Re-identification Test with BG

14

With background With background With background 200200 Original fa Original fb De-id fb

200 x 200 With background Orig De-id PCA + K-NN (Euclidean distance) 54.83% 4.05% LBP + K-NN (Euclidean distance) 83.39% 1.25% HOG + K-NN (Cosine distance) 74.87% 5.92% LPQ + K-NN (Cosine distance) 80.69% 21.91% LPQ + SVM 78.09% 17.45%

Re-identification Test with BG (cont.)

15

With background With background With background 300300 Original fa Original fb De-id fb FERET dataset 300 x 300 With background Without background Orig De-id Orig De-id PCA + k-NN (Euclidean distance) 61.27% 38.94% 42.37% 0% LBP + k-NN (Euclidean distance) 87.23% 54.83% 63.03% 0.21% HOG + k-NN (Cosine distance) 78.09% 56.70% 18.38% 0% LPQ + k-NN (Cosine distance) 82.24% 61.37% 45.79% 0.21% Multi-PIE dataset 300 x 300 With background Without background Orig De-id Orig De-id LBP + k-NN (Euclidean distance) 95.5% 66.96% 76.79% 0.45% LPQ + k-NN (Cosine distance) 96.88% 75.89% 61.16% 0%

Same person?

16

Same person?

17

Potential risk of background

id: 00049 id: 00002 id: 00130 id: 00155 Original fa Original fb De-id fb

300 x 300 inverse crop Orig De-id PCA + k-NN 56.39% 30.11% LBP + k-NN 78.19% 55.24% HOG + k-NN 53.27% 26.17% LPQ + k-NN 60.85% 32.09%

• Inverse crop based on their facial landmarks
• This is a generic attack to any face de-identification

method, which modifies the face region only.

18

Summary of activities during this STSM

• Extensive re-identification tests with FERET and

Multi PIE datasets using different face descriptors and different distance measurements.

• Recognition test of a potential re-identification

attack based on background image region and evaluation of the risk (recognition using background information)

19

Conclusions

• k-Diff-furthest face de-identification method has high

privacy protection performance within the face region.

• However, when the de-identified face region is merged

with the background from the original image, it may significantly increase the risk of re-identification to an unacceptable level.

• To build a complete face de-identified system, not only

the face region need to be considered, but also the soft-biometric and non-biometric parts outside the face region (work of WG2) need to be considered.

20

Questions?

21

Thank you!

22