본문 바로가기
KERD
논문KCI 등재

Secure Object Detection Based on Deep Learning

김건형|정임영
한국정보처리학회|2021.06|JIPS(Journal of Information Processing Systems) (Journal of Information Processing Systems)|제17권 제3호|pp. 571-585|DOI 10.3745/JIPS.03.0161

3

조회

0

다운로드

1

인용

0

참고문헌

키워드

PrivacyIntegrityDeep LearningObject DetectionRobustness

초록

Applications for object detection are expanding as it is automated through artificial intelligence-basedprocessing, such as deep learning, on a large volume of images and videos. High dependence on training dataand a non-transparent way to find answers are the common characteristics of deep learning. Attacks on trainingdata 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 learningenables object recognition in images and videos. This paper summarizes the security issues that need to beaddressed 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.

Abstract

Applications for object detection are expanding as it is automated through artificial intelligence-basedprocessing, such as deep learning, on a large volume of images and videos. High dependence on training dataand a non-transparent way to find answers are the common characteristics of deep learning. Attacks on trainingdata 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 learningenables object recognition in images and videos. This paper summarizes the security issues that need to beaddressed 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.

참고문헌 (50)

  1. S. Dasiopoulou, "Knowledge-assisted semantic video object detection", IEEE Transactions on Circuits and Systems for Video Technology, 15(10), pp.1210~1224 (2005)
  2. D. Cao, "An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks", Human-centric Computing and Information Sciences, 10 (2020)
  3. Y. Liu, "Delving into transferable adversarial examples and blackbox attacks", Proceedings of the 5th International Conference on Learning Representations (ICLR) (2017)
  4. "Transferability in machine learning: from phenomena to black-box attacks using adversarial samples" (2016)[URL]
  5. N. Papernot, "Practical black-box attacks against machine learning", Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, pp.506~519 (2017)
  6. P. Y. Chen, "Zoo: zeroth order optimization based blackbox attacks to deep neural networks without training substitute models", Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (AISec), pp.15~26 (2017)
  7. W. Brendel, "Decision-based adversarial attacks : reliable attacks against blackbox machine learning models", Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
  8. "On detecting adversarial perturbations" (2017)[URL]
  9. "Online data poisoning attacks" (2019)[URL]
  10. C. Burkard, "Analysis of causative attacks against SVMs learning from data streams", Proceedings of the 3rd ACM on International Workshop on Security and Privacy Analytics, pp.31~36 (2017)
  11. "Optimal adversarial attack on autoregressive models by manipulating the environment" (2019)[URL]
  12. B. Li, "Data poisoning attacks on factorization-based collaborative filtering", Advances in Neural Information Processing, 29, pp.1885~1893 (2016)
  13. "Robust physical-world attacks on deep learning models" (2018)[URL]
  14. Y. Dong, "Evading defenses to transferable adversarial examples by translationinvariant attacks", Proceedings of IEEE Conference of Computer Vision and Pattern Recognition (CVPR), pp.4312~4321 (2019)
  15. A. Kurakin, "Adversarial examples in the physical world", Proceedings of the 5th International Conference on Learning Representations (ICLR) (2017)
  16. A. Athalye, "Synthesizing robust adversarial examples", Proceedings of the 35th International Conference on Machine Learning (ICML), pp.284~293 (2018)
  17. I. J. Goodfellow, "Explaining and harnessing adversarial examples", Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2015)
  18. N. Carlini, "Towards evaluating the robustness of neural networks", Proceedings of 2017IEEE Symposium on Security and Privacy, pp.39~57 (2017)
  19. M. J. J. Ghrabat, "An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier", Human-centric Computing and Information Sciences, 9 (2019)
  20. Y. Liu, "Privacy-preserving object detection for medical images with faster R-CNN", IEEE Transactions on Information Forensics and Security (2019)[DOI]
  21. L. Wang, "Compressive sensing of medical images with confidentially homomorphic aggregations", IEEE Internet of Things Journal, 6(2), pp.1402~1409 (2019)
  22. M. Abadi, "Deep learning with differential privacy", Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp.308~318 (2016)
  23. C. Yin, "Local privacy protection classification based on human-centric computing", Human-centric Computing and Information Sciences, 9 (2019)
  24. Q. Jia, "Preserving model privacy for machine learning in distributed systems", IEEE Transactions on Parallel and Distributed Systems, 29(8), pp.1808~1822 (2018)
  25. N. A. Memon, "Watermarking of medical images for content authentication and copyright protection", Ph.D, pp.2010
  26. Chengyou Wang, "LBP and DWT Based Fragile Watermarking for Image Authentication", JIPS(Journal of Information Processing Systems), 14(3), pp.666~679 (2018), 한국정보처리학회[DOI]
  27. Chengyou Wang, "Review on Self-embedding Fragile Watermarking for Image Authentication and Self-recovery", JIPS(Journal of Information Processing Systems), 14(2), pp.510~522 (2018), 한국정보처리학회[DOI]
  28. N. Papernot, "Distillation as a defense to adversarial perturbations against deep neural networks", Proceedings of the 2016 IEEE Symposium on Security & Privacy, pp.582~597 (2016)
  29. "Adversarial learning in statistical classification: a comprehensive review of defenses against attacks" (2019)[URL]
  30. S. Patel, "Trust Management VI", pp.129~141 (2012), Springer
  31. M. Beye, "Efficient privacy preserving k-means clustering in a three-party setting", Proceedings of IEEE International Workshop on Information Forensics and Security, pp.1~6 (2011)
  32. M. S. Riazi, "Chameleon: a hybrid secure computation framework for machine learning applications", Proceedings of the 2018 on Asia Conference on Computer and Communications Security (ASIACCS), pp.707~721 (2018)
  33. X. Wu, "An algorithm for reversible information hiding of encrypted medical images in homomorphic encrypted domain", Discrete & Continuous Dynamical Systems-S, 12(4-5), pp.1441~1455 (2019)
  34. "CaRENets: compact and resource-efficient CNN for homomorphic inference on encrypted medical images" (2019)[URL]
  35. Z. Ma, "Privacy-preserving outsourced speech recognition for smart IoT devices", IEEE Internet of Things Journal, 6(5), pp.8406~8420 (2019)
  36. Y. Zheng, "Privacy-preserving image denoising from external cloud databases", IEEE Transactions on Information Forensics and Security, 12(6), pp.1285~1298 (2017)
  37. M. Noura, "A dynamic approach for a lightweight and secure cipher for medical images", Multimedia Tools and Applications, 77(23), pp.31397~31426 (2018)
  38. K. Y. Chu, "Real-time privacy-preserving moving object detection in the cloud", Proceedings of the 21st ACM International Conference on Multimedia, pp.597~600 (2013)
  39. A. Sen, "Decision and Game Theory for Security", pp.59~79 (2018), Springer
  40. P. Selvaraj, "Whirlpool algorithm with hash function based watermarking algorithm for the secured transmission of digital medical images", Mobile Networks and Applications (2018)[DOI]
  41. S. M. Mousavi, "Watermarking techniques used in medical images : a survey", Journal of Digital Imaging, 27(6), pp.714~729 (2014)
  42. S. Gu, "Towards deep neural network architectures robust to adversarial examples", Proceedings of the 3rd International Conference on Learning Representations (2015)
  43. "Detecting adversarial examples and other misclassifications in neural networks by introspection" (2019)[URL]
  44. F. Tramer, "Ensemble adversarial training : Attacks and defenses", Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
  45. "Defense against adversarial attacks using high-level representation guided denoiser" (2018)[URL]
  46. "Mitigating adversarial effects through randomization" (2018)[URL]
  47. C. Guo, "Countering adversarial images using input transformations", Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
  48. A. Shamir, "How to share a secret", Communications of the ACM, 22(11), pp.612~613 (1979)
  49. C. Dwork, "The algorithmic foundations of differential privacy", Theoretical Computer Science, 9(3-4), pp.211~407 (2014)
  50. D. W. Hosmer Jr, "Applied Logistic Regression" (2013), John Wiley & Sons

관련 논문AI추천

Deep Learning Applied Abnormal Human Behavior Detection in Video Surveillance Systems – A Survey곽내정, 이병엽한국콘텐츠학회 · International Journal of Contents2024 · 제20권 제4호인공지능 기반 스테가노그래피 생성 기술 최신 연구 동향김덕영, 김현지, 서화정, 윤세영, 임세진(사)한국스마트미디어학회 · 스마트미디어저널2023 · 제12권 제4호입력 변이에 따른 딥러닝 모델 취약점 연구 및 검증권태경, 김재욱, 박래현한국정보보호학회 · 정보보호학회논문지2021 · 제31권 제1호Robust architecture search using network adaptation암리타 라나, Kyung Ki Kim한국센서학회 · 센서학회지2021 · 제30권 제5호Adversarial Sample Generation and Training using Neural NetworkHo Yub Jung(사)한국스마트미디어학회 · 스마트미디어저널2024 · 제13권 제10호Violent Activity Detection Using Deep Convolutional Neural Networks in Video Surveillance파트 유 민 울라, 백성욱, 이미영, 이자즈 울 하크, 알타프 후세인한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2021 · 제17권 제4호

이 간행물의 다른 논문 (15건)

A Federated Multi-Task Learning Model Based on Adaptive Distributed Data Latent Correlation AnalysisYibai Wang, Shengbin Wupp. 441-452Attentive Transfer Learning via Self-supervised Learning for Cervical Dysplasia Diagnosis채진영, 김동호, Roger Zimmermann, 김지희pp. 453-461Effective Pre-rating Method Based on Users' Dichotomous Preferences and Average Ratings Fusion for Recommender SystemsXiufang Cheng, Shulin Cheng, Wanyan Wang, Shan Yangpp. 462-472Analysis of Impact on ERP Customization Module Using CSR Data유병근, 김승희pp. 473-488An Offloading Scheduling Strategy with Minimized Power Overhead for Internet of Vehicles Based on Mobile Edge ComputingTianzhang Li, Bo Hepp. 489-504
원문 보기