Mobile sensor data anonymization
Open accessThe 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.
Abstract
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…”
MethodInternational Conference on Learning Representations (ICLR)
Abbas, M. Z. A., Kivinen, J., & Raiko, T. (2016) · Cited by 1,694
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015) · arXiv · doi:10.48550/arxiv.1511.05644 · Cited by 1,579
Bagnall, A., Lines, J., Bostrom, A., Large, J., & Keogh, E. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0483-9 · Cited by 1,377 · cited 1×
“17k -NN with DTW outperforms other methods in time series classification, except when considerable computation and implementation cost is acceptable for very small improvements [2].”
Method(2015) · Cited by 989
Smart Homes for Elderly Healthcare—Recent Advances and Research Challenges
Majumder, S., Aghayi, E., Noferesti, M., Memarzadeh-Tehran, H., Mondal, T., Pang, Z., & Deen, M. (2017) · Sensors · doi:10.3390/s17112496 · Cited by 618 · cited 1×
“using a binary cross-entropy for fall detection [18].”
MethodDifferential privacy under continual observation
Dwork, C., Naor, M., Pitassi, T., & Rothblum, G. N. (2010) · Proceedings of the forty-second ACM symposium on Theory of computing · doi:10.1145/1806689.1806787 · Cited by 583 · cited 1×
“Although differential privacy [8, 34] offers a strong privacy guarantee for X′1j”
BackgroundUtility-Privacy Tradeoffs in Databases: An Information-Theoretic Approach
Sankar, L., Rajagopalan, S. R., & Poor, H. V. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2253320 · Cited by 371 · cited 2×
“Another approach to privacy-preserving data release is based on information theory [17, 28], where the mutual information, between the released data and the latent information which can be drawn from data, is considered as the measure of privacy.”
BackgroundACCessory: password inference using accelerometers on smartphones
Owusu, E., Han, J., Das, S., Perrig, A., & Zhang, J. (2012) · Proceedings of the Twelfth Workshop on Mobile Computing Systems & Applications - HotMobile '12 · doi:10.1145/2162081.2162095 · Cited by 370 · cited 1×
“ser identity for user authentication [22]. However, other untrusted applications with direct access to raw sensory data may infer private information (e.g. inferring passwords from accelerometer data [24]). We are therefore interested in designing a privacy-preserving method that gives apps an ondevice transformed ver…”
MethodExtracting deep bottleneck features using stacked auto-encoders
Gehring, J., Miao, Y., Metze, F., & Waibel, A. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638284 · Cited by 274 · 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.”
BackgroundObstructing Classification via Projection
Haghighatkhah, P., Meulemans, W., Speckmann, B., Urhausen, J., & Verbeek, K. (2021) · Leibniz international proceedings in informatics · doi:10.4230/lipics.mfcs.2021.56 · Cited by 229
An intuitive proof of the data processing inequality
Beaudry, N. J., & Renner, R. (2012) · Quantum Information and Computation · doi:10.26421/qic12.5-6-4 · Cited by 193 · cited 1×
“Therefore the transformation U→ X→ X′ is Markovian [26] and, based on the data processing inequality [3], the following holds: I (U;X) ≥ I (U;X′).”
MethodLearning Human Identity From Motion Patterns
Neverova, N., Wolf, C., Lacey, G., Fridman, L., Chandra, D., Barbello, B., & Taylor, G. (2016) · IEEE Access · doi:10.1109/access.2016.2557846 · Cited by 172
Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12
Jun, T., Korolova, A., Bai, X., Wang, X., & Wang, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.02753 · Cited by 170 · cited 1×
“For the time series of sensor data, we repeatedly observe highly frequent patterns in consecutive data release, and applying the same differentially private mechanism to all of the released time window of data cannot provide a privacy guarantee, unless considerable noise is added to each window, that would eliminate t…”
MethodProtecting sensory data against sensitive inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Spiral (Imperial College London) · Cited by 166
Self-citationContext-Aware Generative Adversarial Privacy
Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. (2017) · Entropy · doi:10.3390/e19120656 · Cited by 156 · cited 3×
“These techniques have been recently applied to calculate mutual information for solving optimization problems [9, 13, 23, 32].”
BackgroundMethodProtecting Sensory Data against Sensitive Inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems · doi:10.1145/3195258.3195260 · Cited by 154
Self-citationOptimal Utility-Privacy Trade-off with the Total Variation Distance as the Privacy Measure
Rassouli, B., & Gündüz, D. (2018) · arXiv.org · doi:10.48550/arxiv.1801.02505 · Cited by 113 · cited 3×
“Therefore the transformation U→ X→ X′ is Markovian [26] and, based on the data processing inequality [3], the following holds: I (U;X) ≥ I (U;X′).”
BackgroundMethodNotice of Removal: Deep Private-Feature Extraction
Osia, S. A., Taheri, A., Shamsabadi, A. S., Katevas, K., Haddadi, H., & Rabiee, H. R. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2878698 · Cited by 109 · cited 3×
“stribution of data or to model, using variational autoencoders (VAE) [14], data with well-known distributions. These techniques can be applied to quantify mutual information for optimization problems [7, 11, 24, 34] and can be used to remove sensitive information from latent low-dimensional representations of the data…”
BackgroundMethodSelf-citationToward accurate dynamic time warping in linear time and space
SalvadorStan, & ChanPhilip (2007) · doi:10.5555/1367985.1367993 · Cited by 103
Censoring Representations with an Adversary
Edwards, H. S., & Storkey, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05897 · Cited by 94 · cited 5×
“ive information [21]. Only considering the latent representation produced by the encoder and leaving intact the decoder with information extracted from the training data offer only limited protection [7, 16]. Considering the decoder’s output leads to a more reliable data protection [20, 26]. In this paper, we consider…”
MethodInfluentialPrivacy-Preserving Adversarial Networks
Tripathy, A., Wang, Y., & Ishwar, P. (2019) · 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton) · doi:10.1109/allerton.2019.8919758 · Cited by 87 · cited 3×
“Practically, we can approximate the mutual information by estimating the posterior distribution of the private variables given the released data [32], using the adversarial training mechanisms [9].”
BackgroundMethodLocal Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
Duchi, J. C., Jordan, M. I., & Wainwright, M. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1305.6000 · Cited by 86 · cited 1×
“eed to aggregate all users’ data in one place1. In our case, we do not trust a data aggregator and want to run the mechanism on the user’s devices. Moreover, The local version of differential privacy [7, 16] is also very challenging for this setting. For the time series of sensor data, we repeatedly observe highly fre…”
BackgroundReplacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
Malekzadeh, M., Clegg, R. G., & Haddadi, H. (2018) · 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00025 · Cited by 76 · cited 1×
“d data are available at: https://github.com/mmalekzadeh/motion-sense model and prevent undesirable memorization [2, 8]. An effective way to train an autoencoder is to randomly corrupt [35] or replace [21] the original input and force the model to refine it in the reconstruction. In this way, a well-trained autoencoder…”
BackgroundSelf-citationMinimax Filter: Learning to Preserve Privacy from Inference Attacks
Hamm, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.03577 · Cited by 45 · cited 1×
“regulates the transformed data to give as little information as possible about the user’s identity; subject to minimum possible distortion in the data to preserve the utility. Unlike other approaches [12, 13, 28, 32] the training process not only regulates the encoder to only consider task-specific features included i…”
BackgroundOlympus: Sensor Privacy through Utility Aware Obfuscation
Raval, N., Machanavajjhala, A., & Pan, J. (2019) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0002 · Cited by 40 · cited 2×
“Considering the decoder’s output leads to a more reliable data protection [20, 26].”
BackgroundA Review of Differential Privacy in Individual Data Release
Wang, J., Liu, S., & Li, Y. (2015) · International Journal of Distributed Sensor Networks · doi:10.1155/2015/259682 · Cited by 33 · cited 1×
“Although differential privacy [8, 34] offers a strong privacy guarantee for X′1j”
BackgroundKatevas, K., Haddadi, H., & Tokarchuk, L. N. (2014) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/2639108.2642910 · Cited by 31 · cited 1×
“quirements of abundance and variety of activities and users5. We therefore collected a dataset from the accelerometer and gyroscope of an iPhone 6s placed in the user’s front pocket of tight trousers [13, 20]. The dataset includes 24 participants, in a range of age, weight, height and gender, who performed 6 activitie…”
MethodSelf-citationDEEProtect: Enabling Inference-based Access Control on Mobile Sensing ApplicationsPreprint
Liu, C., Chakraborty, S., & Mittal, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.06159 · Cited by 28 · cited 3×
“Moreover, a latent representation can be learned that removes some meaningful patterns from the data to reduce the possibility of inferring sensitive information [9, 16].”
BackgroundPrivacy-Preserving Personal Model Training
Servia-Rodríguez, S., Wang, L., Zhao, J., Mortier, R., & Haddadi, H. (2018) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00024 · Cited by 25 · cited 1×
“the training of the AAE, which can be done locally, on the user powerful devices; centrally, by a service provider; or a user can download a public pre-trained model and refined it on their own data [29]. 3 ! !"#$%&'()*+ & ,-.&/-0 .&/1& ,-.&/-0 .&/1& ,-.&/-0.&23 1&…”
BackgroundSelf-citationAn information-aware visualization for privacy-preserving accelerometer data sharing
Xiao, F., Lu, M., Zhao, Y., Menasria, S., Meng, D., Xie, S., Li, J., & Li, C. (2018) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-018-0137-6 · Cited by 19 · 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].”
BackgroundOptimal Utility-Privacy Trade-off with Total Variation Distance as a Privacy Measure
Rassouli, B., & Gündüz, D. (2018) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw.2018.8613451 · Cited by 17
On Information-theoretic Measures for Quantifying Privacy Protection of Time-series Data
Ma, C. Y. T., & Yau, D. K. Y. (2015) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/2714576.2714577 · Cited by 14 · cited 1×
“Another approach to privacy-preserving data release is based on information theory [17, 28], where the mutual information, between the released data and the latent information which can be drawn from data, is considered as the measure of privacy.”
BackgroundDistributed One-Class Learning
Shamsabadi, A. S., Haddadi, H., & Cavallaro, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451093 · Cited by 8
Self-citationUntitled work
Srivastava (2014) · doi:10.5555/2627435.2670313 · cited 3×
“Pooling Dropout ( 0.25) … (512) (128) Dense Layer ReLU (2, 8, 32) (512) Flatten Dropout ( 0.5) (128) (32) Dense Layer ReLU Dropout ( 0.5) (32) (24) Dense Layer SoftMax Figure 5: The DecReg architecture.”
MethodInfluential
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
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.