[논문]Secure Object Detection Based on Deep Learning

Kim, Keonhyeong; Jung, Im Young

doi:10.3745/jips.03.0161

Secure Object Detection Based on Deep Learning 원문보기

Journal of information processing systems, v.17 no.3, 2021년, pp.571 - 585

Kim, Keonhyeong (School of Electronics and Engineering, Kyungpook National University) , Jung, Im Young (School of Electronics and Engineering, Kyungpook National University)

Abstract ▼ AI-Helper

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

주제어

표/그림 (21)

표 Table 1. Security attacks for object detection through deep learning
그림 Fig. 1. A deep learning neural network architecture. Adapted from [28].
그림 Fig. 2. Pairs of normal and adversarial images. Adapted from [28].
그림 Fig. 3. An adversarial crafting process. The model F can misclassify an image using the input of X + δX instead of X. F(X + δX) produces 4 (the adversarial target class) instead of 1 (the original class), and lets an adversarial sample X^* be found. Adapted from [28].
그림 Fig. 4. Linear support vector machines classifier decision boundary. Adapted from [29].
그림 Fig. 5. The attacker injects contaminated samples {a_t}, online for the training samples {z_t}, and the learner's model {θ_t}. Adapted from [9].
그림 Fig. 6. The stop sign is recognized as the speed sign by deep learning. Adapted from [13].
표 Table 2. Recent research for secure object detection
그림 Fig. 7. Privacy-preserving object detection with Fast RNN. Adapted from Liu et al. [20] with the permission of the IEEE.
그림 Fig. 8. Mapping the pixels of the input image to the ciphertext slots. Adapted from [34].
그림 Fig. 9. Vector matrix product in the convolution layer in CaRENets. Adapted from [28].
그림 Fig. 10. A service model based on a garbled circuit. Adapted from Zheng et al. [30] with the permission of the IEEE.
그림 Fig. 11. Moving object detection in encrypted images. Adapted from Chu et al. [38] with the permission of the Association for Computing Machinery.
그림 Fig. 12. Example of training set camouflage: (a) camouflaged training set and (b) secret classification task. Adapted from Sen et al [39] with the permission of Springer Nature.
그림 Fig. 13. Typical watermarking system [25].
그림 Fig. 14. Defensive distillation to transfer knowledge of probability vectors. Adapted from Papernot et al. [28] with the permission of the IEEE.
그림 Fig. 15. Adversarial detector. Adapted from [8].
그림 Fig. 16. Distribution of the average logit values. It appears clearly that the average logit values are higher for correctly classified MNIST images compared with misclassifications. Adapted from [43].
그림 Fig. 17. High-level representation guided denoiser. Adapted from [45].
그림 Fig. 18. Randomization-based defense mechanism. Adapted from [46].
표 Table 3. Issues from existing solutions

참고문헌 (50)

S. Dasiopoulou, V. Mezaris, I. Kompatsiaris, V. Papastathis, and M. Strintzis, "Knowledge-assisted semantic video object detection," IEEE Transactions on Circuits and Systems for Video Technology, vol. 15, no. 10, pp. 1210-1224, 2005.

상세보기
D. Cao, Z. Chen, and L. Gao, "An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks," Human-centric Computing and Information Sciences, vol. 10, article no. 14, 2020.

상세보기
Y. Liu, X. Chen, C. Liu, and D. Song, "Delving into transferable adversarial examples and blackbox attacks," in Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France, 2017.
N. Papernot, P. McDaniel, and I. Goodfellow, "Transferability in machine learning: from phenomena to black-box attacks using adversarial samples," 2016 [Online]. Available: https://arxiv.org/abs/1605.07277.
N. Papernot, P. McDaniel, I. Goodfellow, S. Jha, Z. B. Celik, and A. Swami, "Practical black-box attacks against machine learning," in Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, Abu Dhabi, United Arab Emirates, 2017, pp. 506-519.
P. Y. Chen, H. Zhang, Y. Sharma, J. Yi, and C. J. Hsieh, "Zoo: zeroth order optimization based blackbox attacks to deep neural networks without training substitute models," in Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (AISec), Dallas, TX, 2017, pp. 15-26.
W. Brendel, J. Rauber, and M. Bethge, "Decision-based adversarial attacks: reliable attacks against black-box machine learning models," in Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.
J. H. Metzen, T. Genewein, V. Fischer, and B. Bischoff, "On detecting adversarial perturbations," 2017 [Online]. Available: https://arxiv.org/abs/1702.04267.
X. Zhang, X. Zhu, and L. Lessard, "Online data poisoning attacks," 2019 [Online]. Available: https://arxiv.org/abs/1903.01666.
C. Burkard and B. Lagesse, "Analysis of causative attacks against SVMs learning from data streams," in Proceedings of the 3rd ACM on International Workshop on Security and Privacy Analytics, Scottsdale, AZ, 2017, pp. 31-36.
Y. Chen and X. Zhu, "Optimal adversarial attack on autoregressive models by manipulating the environment," 2019 [Online]. Available: https://arxiv.org/abs/1902.00202.
B. Li, Y. Wang, A. Singh, and Y. Vorobeychik, "Data poisoning attacks on factorization-based collaborative filtering," Advances in Neural Information Processing, vol. 29, pp. 1885-1893, 2016.
K. Eykholt, I. Evtimov, E. Fernandes, B. Li, A. Rahmati, C. Xiao, A. Prakash, T. Kohno, and D. Song, "Robust physical-world attacks on deep learning models," 2018 [Online]. Available: https://arxiv.org/abs/1707.08945.
Y. Dong, T. Pang, H. Su, and J. Zhu, "Evading defenses to transferable adversarial examples by translation-invariant attacks," in Proceedings of IEEE Conference of Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019, pp. 4312-4321.
A. Kurakin, I. Goodfellow, S. Bengio, "Adversarial examples in the physical world," in Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France, 2017.
A. Athalye, L. Engstrom, A. Ilyas, and K. Kwok, "Synthesizing robust adversarial examples," in Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018, pp. 284-293.
I. J. Goodfellow, J. Shlens, and C. Szegedy, "Explaining and harnessing adversarial examples," in Proceedings of the 3rd International Conference on Learning Representations(ICLR), San Diego, CA, 2015.
N. Carlini and D. Wagner, "Towards evaluating the robustness of neural networks," in Proceedings of 2017 IEEE Symposium on Security and Privacy, San Jose, CA, 2017, pp. 39-57.
M. J. J. Ghrabat, G. Ma, I. Y. Maolood, S. S. Alresheedi, and Z. A. Abduljabbar, "An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier," Human-centric Computing and Information Sciences, vol. 9, article no. 31, 2019.

상세보기
Y. Liu, Z. Ma, X. Liu, S. Ma, and K. Ren, "Privacy-preserving object detection for medical images with faster R-CNN," IEEE Transactions on Information Forensics and Security, 2019. https://doi.org/10.1109/TIFS.2019.2946476

상세보기
L. Wang, L. Li, J. Li, J. Li, B. B. Gupta, and L. Xia, "Compressive sensing of medical images with confidentially homomorphic aggregations," IEEE Internet of Things Journal, vol. 6, no. 2, pp. 1402-1409, 2019.

상세보기
M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, "Deep learning with differential privacy," in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria, 2016, pp. 308-318.
C. Yin, B. Zhou, Z. Yin, and J. Wang, "Local privacy protection classification based on human-centric computing," Human-centric Computing and Information Sciences, vol. 9, article no. 33, 2019.

상세보기
Q. Jia, L. Guo, Z. Jin, and Y. Fang, "Preserving model privacy for machine learning in distributed systems," IEEE Transactions on Parallel and Distributed Systems, vol. 29, no. 8, pp. 1808-1822, 2018.

상세보기
N. A. Memon, "Watermarking of medical images for content authentication and copyright protection," Ph.D. dissertation, GIK Institute of Engineering Sciences and Technology, Topi, Pakistan, 2010.
C. Wang, H. Zhang, X. Zhou, "LBP and DWT based fragile watermarking for image authentication," Journal of Information Processing Systems, vol. 14, no. 3, pp. 666-679, 2018.

원문보기 상세보기
C. Wang, H. Zhang, and X. Zhou, "Review on self-embedding fragile watermarking for image authentication and self-recovery," Journal of Information Processing Systems, vol. 14, no. 2, pp. 510-522, 2018.

원문보기 상세보기
N. Papernot, P. McDaniel, X. Wu, S. Jha, and A. Swami, "Distillation as a defense to adversarial perturbations against deep neural networks," in Proceedings of the 2016 IEEE Symposium on Security & Privacy, San Jose, CA, 2016, pp. 582-597.
D. J. Miller, Z. Xiang, and G. Kesidis, "Adversarial learning in statistical classification: a comprehensive review of defenses against attacks," 2019 [Online]. Available: https://arxiv.org/abs/1904.06292.
S. Patel, S. Garasia, and D. Jinwala, "An efficient approach for privacy preserving distributed k-means clustering based on Shamir's secret sharing scheme," in Trust Management VI. Heidelberg, Germany: Springer, 2012, pp. 129-141.
M. Beye, Z. Erkin, and R. L. Lagendijk, "Efficient privacy preserving k-means clustering in a three-party setting," in Proceedings of IEEE International Workshop on Information Forensics and Security, Iguacu Falls, Argentina, 2011, pp. 1-6.
M. S. Riazi, C. Weinert, O. Tkachenko, E. M. Songhori, T. Schneider, and F. Koushanfar, "Chameleon: a hybrid secure computation framework for machine learning applications," in Proceedings of the 2018 on Asia Conference on Computer and Communications Security (ASIACCS), Incheon, Republic of Korea, 2018, PP. 707-721.
X. Wu, "An algorithm for reversible information hiding of encrypted medical images in homomorphic encrypted domain," Discrete & Continuous Dynamical Systems-S, vol. 12, no. 4-5, pp. 1441-1455, 2019.
J. Chao, A. A. Badawi, B. Unnikrishnan, J. Lin, C. F. Mun, J. M. Brown, et al., "CaRENets: compact and resource-efficient CNN for homomorphic inference on encrypted medical images," 2019 [Online]. Available: https://arxiv.org/abs/1901.10074.
Z. Ma, Y. Liu, X. Liu, J. Ma, and F. Li, "Privacy-preserving outsourced speech recognition for smart IoT devices," IEEE Internet of Things Journal, vol. 6, no. 5, pp. 8406-8420, 2019.

상세보기
Y. Zheng, H. Cui, C. Wang, and J. Zhou, "Privacy-preserving image denoising from external cloud databases," IEEE Transactions on Information Forensics and Security, vol. 12, no. 6, pp. 1285-1298, 2017.

상세보기
M. Noura, H. Noura, A. Chehab, M. M. Mansour, L. Sleem, and R. Couturier, "A dynamic approach for a lightweight and secure cipher for medical images," Multimedia Tools and Applications, vol. 77, no. 23, pp. 31397-31426, 2018.

상세보기
K. Y. Chu, Y. H. Kuo, and W. H. Hsu, "Real-time privacy-preserving moving object detection in the cloud," in Proceedings of the 21st ACM International Conference on Multimedia, Barcelona, Spain, 2013, pp. 597-600.
A. Sen, S. Alfeld, X. Zhang, A. Vartanian, Y. Ma, and X. Zhu, "Training set camouflage," in Decision and Game Theory for Security. Cham, Switzerland: Springer, 2018, pp. 59-79.
P. Selvaraj and R. Varatharajan, "Whirlpool algorithm with hash function based watermarking algorithm for the secured transmission of digital medical images," Mobile Networks and Applications, 2018. https://doi.org/10.1007/s11036-018-1057-4
S. M. Mousavi, A. Naghsh, and S. Abu-Bakar, "Watermarking techniques used in medical images: a survey," Journal of Digital Imaging, vol. 27, no. 6, pp. 714-729, 2014.

상세보기
S. Gu and L. Rigazio, "Towards deep neural network architectures robust to adversarial examples," in Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, 2015.
J. Aigrain and M. Detyniecki, "Detecting adversarial examples and other misclassifications in neural networks by introspection," 2019 [Online]. https://arxiv.org/abs/1905.09186.
F. Tramer, A. Kurakin, N. Papernot, D. Boneh, and P. McDaniel, "Ensemble adversarial training: Attacks and defenses," in Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.
F. Liao, M. Liang, Y. Dong, T. Pang, X. Hu, and J. Zhu, "Defense against adversarial attacks using high-level representation guided denoiser," 2018 [Online]. Available: https://arxiv.org/abs/1712.02976.
C. Xie, J. Wang, Z. Zhang, Z. Ren, and A. Yuille, "Mitigating adversarial effects through randomization," 2018 [Online]. Available: https://arxiv.org/abs/1711.01991.
C. Guo, M. Rana, M. Cisse, and L. V. D. Maaten, "Countering adversarial images using input transformations," in Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.
A. Shamir, "How to share a secret," Communications of the ACM, vol. 22, no. 11, pp. 612-613, 1979.

상세보기
C. Dwork and A. Roth, "The algorithmic foundations of differential privacy," Theoretical Computer Science, vol. 9, nos. 3-4, pp. 211-407, 2014.
D. W. Hosmer Jr, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression. Hoboken, NJ: John Wiley & Sons, 2013.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증