Tiankuo Wei
ABSTRACT
As an important component of Cyber-Physical Systems (CPS), wireless sensor network faces challenges of computation, communication and privacy. For employing DNN with large capacity in CPS, splitting computing (SC) is proposed, in which transmitting intermediate data is the bottleneck of system efficiency. In this paper, targeting to the compression and privacy limitations occur in the original extracted feature data, we proposed a privacy-preserved intermediate feature compression framework. Therein, a hybrid feature compression module composed of a knowledge-based adaptor network and a traditional video codec is proposed. A noise-based privacy enhancement and domain-concentration cooperative privacy preserving approach is developed. Evaluations are conducted on two DNN models among two datasets, proving the proposed method can achieve better analysis accuracy as well as higher degree of privacy preserving than HEVC.
- Ivan V Bajić, Weisi Lin, and Yonghong Tian. 2021. Collaborative intelligence: Challenges and opportunities. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 8493–8497.Google Scholar
Cross Ref
- Xinlei Chen, Susu Xu, Jun Han, Haohao Fu, Xidong Pi, Carlee Joe-Wong, Yong Li, Lin Zhang, Hae Young Noh, and Pei Zhang. 2020. Pas: Prediction-based actuation system for city-scale ridesharing vehicular mobile crowdsensing. IEEE Internet of Things Journal 7, 5 (2020), 3719–3734.Google ScholarCross Ref
- Xinlei Chen, Susu Xu, Xinyu Liu, Xiangxiang Xu, Hae Young Noh, Lin Zhang, and Pei Zhang. 2020. Adaptive hybrid model-enabled sensing system (HMSS) for mobile fine-grained air pollution estimation. IEEE Transactions on Mobile Computing 21, 6 (2020), 1927–1944.Google ScholarCross Ref
- Xinlei Chen, Yulei Zhao, and Yong Li. 2019. QoE-aware wireless video communications for emotion-aware intelligent systems: A multi-layered collaboration approach. Information Fusion 47(2019), 1–9.Google ScholarCross Ref
- Zhuo Chen, Ling-Yu Duan, Shiqi Wang, Weisi Lin, and Alex C Kot. 2020. Data representation in hybrid coding framework for feature maps compression. In Proceedings of IEEE International Conference on Image Processing. 3094–3098.Google ScholarCross Ref
- Zhuo Chen, Kui Fan, Shiqi Wang, Lingyu Duan, Weisi Lin, and Alex Chichung Kot. 2019. Toward intelligent sensing: Intermediate deep feature compression. IEEE Transactions on Image Processing 29 (2019), 2230–2243.Google ScholarDigital Library
- Zhuo Chen, Kui Fan, Shiqi Wang, Ling-Yu Duan, Weisi Lin, and Alex Kot. 2019. Lossy intermediate deep learning feature compression and evaluation. In Proceedings of the ACM International Conference on Multimedia. 2414–2422.Google ScholarDigital Library
- Hyomin Choi and Ivan V Bajić. 2018. Deep feature compression for collaborative object detection. In Proceedings of IEEE International Conference on Image Processing. 3743–3747.Google ScholarCross Ref
- Hyomin Choi and Ivan V Bajić. 2018. Near-lossless deep feature compression for collaborative intelligence. In Proceedings of IEEE International Workshop on Multimedia Signal Processing. 1–6.Google ScholarCross Ref
- Robert A Cohen, Hyomin Choi, and Ivan V Bajić. 2021. Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence. IEEE Open Journal of Circuits and Systems 2 (2021), 350–362.Google ScholarCross Ref
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 248–255.Google ScholarCross Ref
- Amir Erfan Eshratifar, Amirhossein Esmaili, and Massoud Pedram. 2019. Bottlenet: A deep learning architecture for intelligent mobile cloud computing services. In Proceedings of IEEE/ACM International Symposium on Low Power Electronics and Design. 1–6.Google ScholarCross Ref
- Lixin Fan, Kam Woh Ng, Ce Ju, Tianyu Zhang, Chang Liu, Chee Seng Chan, and Qiang Yang. 2020. Rethinking privacy preserving deep learning: How to evaluate and thwart privacy attacks. In Federated Learning. 32–50.Google Scholar
- Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In Proceedings of International Conference on Machine Learning. 1180–1189.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google ScholarCross Ref
- Yuzhang Hu, Sifeng Xia, Wenhan Yang, and Jiaying Liu. 2020. Sensitivity-Aware Bit Allocation for Intermediate Deep Feature Compression. In Proceedings of IEEE International Conference on Visual Communications and Image Processing. 475–478.Google ScholarCross Ref
- Mikolaj Jankowski, Deniz Gündüz, and Krystian Mikolajczyk. 2020. Joint device-edge inference over wireless links with pruning. In Proceedings of IEEE International Workshop on Signal Processing Advances in Wireless Communications. 1–5.Google ScholarCross Ref
- Linshan Jiang, Xin Lou, Rui Tan, and Jun Zhao. 2019. Differentially Private Collaborative Learning for the IoT Edge.. In Proceedings of International Conference on Embedded Wireless Systems and Networks. 341–346.Google Scholar
- Alex Krizhevsky, Geoffrey Hinton, 2009. Learning multiple layers of features from tiny images. (2009).Google Scholar
- Edward A Lee. 2008. Cyber physical systems: Design challenges. In Proceedings of IEEE International Symposium on Object and Component-oriented Real-time Distributed Computing. 363–369.Google ScholarDigital Library
- Lingjuan Lyu, James C Bezdek, Jiong Jin, and Yang Yang. 2020. FORESEEN: Towards differentially private deep inference for intelligent Internet of Things. IEEE Journal on Selected Areas in Communications 38, 10(2020), 2418–2429.Google ScholarCross Ref
- Yunlong Mao, Shanhe Yi, Qun Li, Jinghao Feng, Fengyuan Xu, and Sheng Zhong. 2018. Learning from differentially private neural activations with edge computing. In Proceedings of IEEE/ACM Symposium on Edge Computing. 90–102.Google ScholarCross Ref
- Yoshitomo Matsubara and Marco Levorato. 2021. Neural compression and filtering for edge-assisted real-time object detection in challenged networks. In Proceedings of International Conference on Pattern Recognition. 2272–2279.Google ScholarCross Ref
- Yoshitomo Matsubara, Marco Levorato, and Francesco Restuccia. 2021. Split computing and early exiting for deep learning applications: Survey and research challenges. Comput. Surveys (2021), 1–28.Google Scholar
- Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Taha Elthakeb, Dean Tullsen, and Hadi Esmaeilzadeh. 2021. Not all features are equal: Discovering essential features for preserving prediction privacy. In Proceedings of the Web Conference. 669–680.Google ScholarDigital Library
- Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Ali Jalali, Dean Tullsen, and Hadi Esmaeilzadeh. 2020. Shredder: Learning noise distributions to protect inference privacy. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems. 3–18.Google ScholarDigital Library
- Claude Elwood Shannon. 1948. A mathematical theory of communication. The Bell system technical journal 27, 3 (1948), 379–423.Google Scholar
- Jiawei Shao and Jun Zhang. 2020. Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems. In Proceedings of IEEE International Conference on Communications Workshops. 1–6.Google ScholarCross Ref
- Gary J Sullivan, Jens-Rainer Ohm, Woo-Jin Han, and Thomas Wiegand. 2012. Overview of the high efficiency video coding (HEVC) standard. IEEE Transactions on Circuits and Systems for Video Technology 22, 12(2012), 1649–1668.Google ScholarDigital Library
- Satoshi Suzuki, Shoichiro Takeda, Motohiro Takagi, Ryuichi Tanida, Hideaki Kimata, and Hayaru Shouno. 2021. Deep Feature Compression using Spatio-Temporal Arrangement toward Collaborative Intelligent World. IEEE Transactions on Circuits and Systems for Video Technology (2021). doi: 10.1109/TCSVT.2021.3107716.Google Scholar
- MTCAJ Thomas and A Thomas Joy. 2006. Elements of information theory. Wiley-Interscience.Google Scholar
- Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In Proceedings of IEEE Information Theory Workshop. 1–5.Google ScholarCross Ref
- Tom Titcombe, Adam J Hall, Pavlos Papadopoulos, and Daniele Romanini. 2021. Practical defences against model inversion attacks for split neural networks. In Proceedings of International Conference on Learning Representations Workshop on Distributed and Private Machine Learning. 1–10.Google Scholar
- Ji Wang, Jianguo Zhang, Weidong Bao, Xiaomin Zhu, Bokai Cao, and Philip S Yu. 2018. Not just privacy: Improving performance of private deep learning in mobile cloud. In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery & Data mining. 2407–2416.Google ScholarDigital Library
- Ziteng Wang, Chun Hu, Dezhi Zheng, and Xinlei Chen. 2021. Ultralow-Power Sensing Framework for Internet of Things: A Smart Gas Meter as a Case. IEEE Internet of Things Journal 9, 10 (2021), 7533–7544.Google ScholarCross Ref
- Zixi Wang, Fan Li, Jing Xu, and Pamela C. Cosman. 2022. Human-Machine Interaction-Oriented Image Coding for Resource-Constrained Visual Monitoring in IoT. IEEE Internet of Things Journal 9, 17 (2022), 16181–16195.Google ScholarCross Ref
- Fang-Jing Wu, Yu-Fen Kao, and Yu-Chee Tseng. 2011. From wireless sensor networks towards cyber physical systems. Pervasive and Mobile computing 7, 4 (2011), 397–413.Google Scholar
- Li Da Xu and Lian Duan. 2019. Big data for cyber physical systems in industry 4.0: a survey. Enterprise Information Systems 13, 2 (2019), 148–169.Google ScholarCross Ref
- Susu Xu, Xinlei Chen, Xidong Pi, Carlee Joe-Wong, Pei Zhang, and Hae Young Noh. 2019. ilocus: Incentivizing vehicle mobility to optimize sensing distribution in crowd sensing. IEEE Transactions on Mobile Computing 19, 8 (2019), 1831–1847.Google Scholar
- Liekang Zeng, En Li, Zhi Zhou, and Xu Chen. 2019. Boomerang: On-demand cooperative deep neural network inference for edge intelligence on the industrial Internet of Things. IEEE Network 33, 5 (2019), 96–103.Google ScholarDigital Library
- Lingchen Zhao, Qian Wang, Qin Zou, Yan Zhang, and Yanjiao Chen. 2019. Privacy-preserving collaborative deep learning with unreliable participants. IEEE Transactions on Information Forensics and Security 15 (2019), 1486–1500.Google ScholarDigital Library
Index Terms
- Privacy-preserved Intermediate Feature Compression for Cyber-Physical Systems
Recommendations
Privacy-preserved Intermediate Feature Compression for Cyber-Physical Systems
UbiComp/ISWC '22 Adjunct: Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable ComputersAs an important component of Cyber-Physical Systems (CPS), wireless sensor network faces challenges of computation, communication and privacy. For employing DNN with large capacity in CPS, splitting computing (SC) is proposed, in which transmitting ...
Privacy-preserving topic model for tagging recommender systems
Tagging recommender systems provide users the freedom to explore tags and obtain recommendations. The releasing and sharing of these tagging datasets will accelerate both commercial and research work on recommender systems. However, releasing the ...
A Framework for Privacy-Preserving Data Publishing with Enhanced Utility for Cyber-Physical Systems
Special Issue on BuildSys'17Cyber-physical systems have enabled the collection of massive amounts of data in an unprecedented level of spatial and temporal granularity. Publishing these data can prosper big data research, which, in turn, helps improve overall system efficiency and ...
Comments