The DOI matches its Crossref record; 43 of the 44 references it cites were found in a registry or an index, and 1 are not checked yet.
Mobile sensor data anonymization
Open accessAbstract
Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions. Raw data streams from motion sensors embedded in portable and wearable devices may reveal private information about users without their awareness. For example, motion data might disclose the weight or gender of a user, or enable their re-identification. To address this problem, we propose an on-device transformation of sensor data to be shared for specific applications, such as monitoring selected daily activities, without revealing information that enables user identification. We formulate the anonymization problem using an information-theoretic approach and propose a new multi-objective loss function for training deep autoencoders. This loss function helps minimizing user-identity information as well as data distortion to preserve the application-specific utility. The training process regulates the encoder to disregard user-identifiable patterns and tunes the decoder to shape the output independently of users in the training set. The trained autoencoder can be deployed on a mobile or wearable device to anonymize sensor data even for users who are not included in the training dataset. Data from 24 users transformed by the proposed anonymizing autoencoder lead to a promising trade-off between utility and privacy, with an accuracy for activity recognition above 92% and an accuracy for user identification below 7%.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Multiple works have proposed privacy preservation methods while classifying human activities, including the replacement auto-encoder, the guardian, estimator, and neutralizer (GEN) architecture [128], and the anonymizing autoencoder [129].”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [129]
In the citing paper
“Experiments performed on a self-collected dataset from the accelerometer and gyroscope showcased excellent activity recognition performance (above 92%) while keeping user identification accuracy below 7%.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [129]
In the citing paper
“Unlike most works, where the output to the encoder is used as features for classification, this work utilizes both the encoder and decoder outputs.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [129]
In the citing paper
“Similarly, the same authors have proposed another anonymizing autoencoder in [129] for classifying different activities while reducing user identification accuracy.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [129]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(2014) · Cited by 33,419
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 2×
“with variational auto-encoders (VAE) [14]).”
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“The information bottleneck [4, 10] in the middle layer of the CAE helps the encoding part of the CAE to capture the main factors of variation in the data into this latent representation.”
BackgroundExtracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · cited 3×
“A simple way to train CAE is to randomly corrupt the input and force the model to refine it in the reconstruction [33].”
BackgroundMethodInfluentialDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 1×
“Existing solutions need a trusted party to have access to users’ personal data to offer a reliable data distortion mechanism [16, 23, 35] or need to ask users to participate in a privacy-preserving training mechanism [1].”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Extracting qualitative dynamics from experimental data
Broomhead, D. S., & King, G. P. (1986) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(86)90031-x · Cited by 2,278 · cited 1×
“pling on activity recognition can be ignored for a rates greater than 20Hz. However, even at 5Hz, we can distinguish the 24 users from each other with over 60% accuracy. SingularSpectrumAnalysis(SSA) [3] decomposes time series into interpretable components such as trend, period, and structureless (or noise) components…”
BackgroundStacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
Masci, J., Meier, U., Cireşan, D., & Schmidhuber, J. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_7 · Cited by 1,955 · cited 2×
“nspired by recent advances in adversarial training to discover from raw data useful representations for a specific task [19], we propose a new multi-objective loss function to train deep autoencoders [22]. The loss function regulates the transformed data to keep as little information as possible about user identity, s…”
BackgroundToward accurate dynamic time warping in linear time and space
Salvador, S., & Chan, P. (2007) · Intelligent Data Analysis · doi:10.3233/ida-2007-11508 · Cited by 1,705 · cited 1×
“ransformation. The k-Nearest Neighbors. To evaluate the efficiency of the anonymization with another unsupervised mechanism, we implement thek-Nearest Neighbors (k-NN) with Dynamic Time Warping (DTW) [27], which is one of the best methods for clustering time series data17. Using DTW, we measure the similarity between…”
Method
Research works printed but not linked: 7
- J. Burke , D. Estrin , M. Hansen , A. Parker , N. Ramanathan , S. Reddy , and M. B. Srivastava . 2006. Participatory sensing . In Workshop on World-Sensor-Web (WSW'06) : Mobile Device Centric Sensor Networks and Applications. 117--134. J. Burke, D. Estrin, M. Hansen, A. Parker, N. Ramanathan, S. Reddy, and M. B. Srivastava. 2006. Participatory sensing. In Workshop on World-Sensor-Web (WSW'06): Mobile Device Centric Sensor Networks and Applications. 117--134.
- Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680. Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.
- 10.5555/3122009.3208010 · doi:10.5555/3122009.3208010
- Yann LeCun and Yoshua Bengio . 1995. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks 3361, 10 ( 1995 ), 1995. Yann LeCun and Yoshua Bengio. 1995. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks 3361, 10 (1995), 1995.
- 10.5555/2029556.2029563 · doi:10.5555/2029556.2029563
- Seyed Ali Osia , Ali Taheri , Ali Shahin Shamsabadi , Kleomenis Katevas , Hamed Haddadi , and Hamid R Rabiee . 2019 . Deep Private-Feature Extraction . IEEE Transactions on Knowledge and Data Engineering. Seyed Ali Osia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, and Hamid R Rabiee. 2019. Deep Private-Feature Extraction. IEEE Transactions on Knowledge and Data Engineering.
- Apple Differential Privacy Team . 2017. Learning with privacy at scale. Online at: https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html ( 2017 ). Apple Differential Privacy Team. 2017. Learning with privacy at scale. Online at: https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html (2017).
Cited by
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
“raining process. For example, Iwasawa et al. [65] proposed to integrate an adversarial loss with the standard activity classification loss to minimize the user identification accuracy. The authors of [92] and [91] also adopted the similar idea to prevent privacy leakage. Their experiment results show an effective redu…”
BackgroundDeep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625
“Similarly, the same authors have proposed another anonymizing autoencoder in [182] for classifying different activities while reducing user identification accuracy.”
BackgroundMethodSensing, Computing, and Communications for Energy Harvesting IoTs: A Survey
Ma, D., Lan, G., Hassan, M., Hu, W., & Das, S. K. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2962526 · Cited by 336
“Most recently, deep learning based privacy-preserving has been investigated as well [196].”
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
“raining process. For example, Iwasawa et al. [65] proposed to integrate an adversarial loss with the standard activity classification loss to minimize the user identification accuracy. The authors of [92] and [91] also adopted the similar idea to prevent privacy leakage. Their experiment results show an effective redu…”
BackgroundA systematic review of smartphone-based human activity recognition methods for health research
Straczkiewicz, M., James, P., & Onnela, J.-P. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00514-4 · Cited by 247
Metadata
- Authors
- Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H.
- Affiliations
- Queen Mary University of London (GB)
- Imperial College London (GB)
- Venue
- Proceedings of the International Conference on Internet of Things Design and Implementation
- Publisher
- ACM
- Published
- 2019-04-15
- Pages
- 49-58
- OpenAlex
- W2898186212
- Cited by
- 298
- References
- 43
- Citations by year
- 2026: 48 · 2025: 64 · 2024: 48 · 2023: 40 · 2022: 28 · 2021: 33 · 2020: 23 · 2019: 13
- FWCI
- 9.28
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Spiral (Imperial College London) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Life Sciences Initiative at Queen Mary University London
- Microsoft Azure for Research Award (CRM:0740917)
- EPSRC Databox (EP/N028260/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- motion sensors, wearable devices, deep autoencoder, multi-objective loss function, information-theoretic privacy, user re-identification, privacy-utility trade-off, activity recognition, accelerometer, gyroscope
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Mobile sensor data anonymization. https://app.cochat.ai/papers/10.1145/3302505.3310068
- The paper
- Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2019). Mobile sensor data anonymization. Proceedings of the International Conference on Internet of Things Design and Implementation. https://doi.org/10.1145/3302505.3310068
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.