{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:11:45Z","timestamp":1772910705902,"version":"3.50.1"},"reference-count":52,"publisher":"Privacy Enhancing Technologies Symposium Advisory Board","issue":"1","license":[{"start":{"date-parts":[[2018,12,24]],"date-time":"2018-12-24T00:00:00Z","timestamp":1545609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Personal data garnered from various sensors are often offloaded by applications to the cloud for analytics. This leads to a potential risk of disclosing private user information. We observe that the analytics run on the cloud are often limited to a machine learning model such as predicting a user\u2019s activity using an activity classifier. We present O<jats:sc>lympus<\/jats:sc>, a privacy framework that limits the risk of disclosing private user information by obfuscating sensor data while minimally affecting the functionality the data are intended for. O<jats:sc>lympus<\/jats:sc> achieves privacy by designing a <jats:italic>utility aware obfuscation<\/jats:italic> mechanism, where privacy and utility requirements are modeled as adversarial networks. By rigorous and comprehensive evaluation on a real world app and on benchmark datasets, we show that O<jats:sc>lympus<\/jats:sc> successfully limits the disclosure of private information without significantly affecting functionality of the application.<\/jats:p>","DOI":"10.2478\/popets-2019-0002","type":"journal-article","created":{"date-parts":[[2019,1,3]],"date-time":"2019-01-03T17:48:20Z","timestamp":1546537700000},"page":"5-25","source":"Crossref","is-referenced-by-count":25,"title":["Olympus: Sensor Privacy through Utility Aware Obfuscation"],"prefix":"10.56553","volume":"2019","author":[{"given":"Nisarg","family":"Raval","sequence":"first","affiliation":[{"name":"Duke University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashwin","family":"Machanavajjhala","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerry","family":"Pan","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"35752","published-online":{"date-parts":[[2018,12,24]]},"reference":[{"key":"2022050321464850722_j_popets-2019-0002_ref_001_w2aab3b7b2b1b6b1ab1ab1Aa","unstructured":"[1] AT&T Database of Faces. http:\/\/www.cl.cam.ac.uk\/research\/dtg\/attarchive\/facedatabase.html."},{"key":"2022050321464850722_j_popets-2019-0002_ref_002_w2aab3b7b2b1b6b1ab1ab2Aa","unstructured":"[2] Deep learning for mobile:dl4mobile. https:\/\/play.google.com\/store\/apps\/details?id=com.nalsil.tensorflowsimapp&hl=en."},{"key":"2022050321464850722_j_popets-2019-0002_ref_003_w2aab3b7b2b1b6b1ab1ab3Aa","unstructured":"[3] Google Cloud AI. https:\/\/cloud.google.com\/products\/machine-learning\/."},{"key":"2022050321464850722_j_popets-2019-0002_ref_004_w2aab3b7b2b1b6b1ab1ab4Aa","unstructured":"[4] Human activity recognition using cnn. https:\/\/github.com\/aqibsaeed\/Human-Activity-Recognition-using-CNN."},{"key":"2022050321464850722_j_popets-2019-0002_ref_005_w2aab3b7b2b1b6b1ab1ab5Aa","unstructured":"[5] Speech recognition tensorflow machine learning. https:\/\/play.google.com\/store\/apps\/details?id=machinelearning.tensorflow.speech&hl=en."},{"key":"2022050321464850722_j_popets-2019-0002_ref_006_w2aab3b7b2b1b6b1ab1ab6Aa","unstructured":"[6] State Farm Distracted Driver Detection. https:\/\/www.kaggle.com\/c\/state-farm-distracted-driver-detection\/data."},{"key":"2022050321464850722_j_popets-2019-0002_ref_007_w2aab3b7b2b1b6b1ab1ab7Aa","unstructured":"[7] TensorFlow Inference API. https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/contrib\/android."},{"key":"2022050321464850722_j_popets-2019-0002_ref_008_w2aab3b7b2b1b6b1ab1ab8Aa","unstructured":"[8] TensorFlow Models. https:\/\/github.com\/tensorflow\/models."},{"key":"2022050321464850722_j_popets-2019-0002_ref_009_w2aab3b7b2b1b6b1ab1ab9Aa","unstructured":"[9] Youtube official blog. Blur moving objects in your video with the new custom blurring tool on youtube. https:\/\/youtube-creators.googleblog.com\/2016\/02\/blur-moving-objects-in-your-video-with.html, 2016."},{"key":"2022050321464850722_j_popets-2019-0002_ref_010_w2aab3b7b2b1b6b1ab1ac10Aa","unstructured":"[10] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng. Tensorflow: A system for large-scale machine learning. OSDI, 2016."},{"key":"2022050321464850722_j_popets-2019-0002_ref_011_w2aab3b7b2b1b6b1ab1ac11Aa","doi-asserted-by":"crossref","unstructured":"[11] P. Aditya, R. Sen, P. Druschel, S. Joon Oh, R. Benenson, M. Fritz, B. Schiele, B. Bhattacharjee, and T. T. Wu. I-pic: A platform for privacy-compliant image capture. MobiSys, 2016.10.1145\/2906388.2906412","DOI":"10.1145\/2906388.2906412"},{"key":"2022050321464850722_j_popets-2019-0002_ref_012_w2aab3b7b2b1b6b1ab1ac12Aa","doi-asserted-by":"crossref","unstructured":"[12] M. Alzantot, S. Chakraborty, and M. B. Srivastava. Sensegen: A deep learning architecture for synthetic sensor data generation. BICA, 2017.10.1109\/PERCOMW.2017.7917555","DOI":"10.1109\/PERCOMW.2017.7917555"},{"key":"2022050321464850722_j_popets-2019-0002_ref_013_w2aab3b7b2b1b6b1ab1ac13Aa","unstructured":"[13] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. ESANN, 2013."},{"key":"2022050321464850722_j_popets-2019-0002_ref_014_w2aab3b7b2b1b6b1ab1ac14Aa","doi-asserted-by":"crossref","unstructured":"[14] R. Chavarriaga, H. Sagha, A. Calatroni, S. T. Digumarti, G. Tr\u00f6ster, J. D. R. Mill\u00e1n, and D. Roggen. The opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recogn. Lett., 2013.10.1016\/j.patrec.2012.12.014","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"2022050321464850722_j_popets-2019-0002_ref_015_w2aab3b7b2b1b6b1ab1ac15Aa","doi-asserted-by":"crossref","unstructured":"[15] J. Chen, J. Konrad, and P. Ishwar. Vgan-based image representation learning for privacy-preserving facial expression recognition. CVPR Workshops, 2018.10.1109\/CVPRW.2018.00207","DOI":"10.1109\/CVPRW.2018.00207"},{"key":"2022050321464850722_j_popets-2019-0002_ref_016_w2aab3b7b2b1b6b1ab1ac16Aa","unstructured":"[16] F. Chollet. keras. https:\/\/github.com\/fchollet\/keras, 2015."},{"key":"2022050321464850722_j_popets-2019-0002_ref_017_w2aab3b7b2b1b6b1ab1ac17Aa","unstructured":"[17] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. CVPR, 2005."},{"key":"2022050321464850722_j_popets-2019-0002_ref_018_w2aab3b7b2b1b6b1ab1ac18Aa","unstructured":"[18] H. Edwards and A. J. Storkey. Censoring representations with an adversary. ICLR, 2016."},{"key":"2022050321464850722_j_popets-2019-0002_ref_019_w2aab3b7b2b1b6b1ab1ac19Aa","unstructured":"[19] M. Erdogdu, N. Fawaz, and A. Montanari. Privacy-utility trade-off for time-series with application to smart-meter data. AAAI Workshops, 2015."},{"key":"2022050321464850722_j_popets-2019-0002_ref_020_w2aab3b7b2b1b6b1ab1ac20Aa","unstructured":"[20] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. NIPS, 2014."},{"key":"2022050321464850722_j_popets-2019-0002_ref_021_w2aab3b7b2b1b6b1ab1ac21Aa","unstructured":"[21] J. Hamm. Minimax filter: Learning to preserve privacy from inference attacks. JMLR, 2017."},{"key":"2022050321464850722_j_popets-2019-0002_ref_022_w2aab3b7b2b1b6b1ab1ac22Aa","doi-asserted-by":"crossref","unstructured":"[22] C. Huang, P. Kairouz, X. Chen, L. Sankar, and R. Rajagopal. Context-aware generative adversarial privacy. Entropy, 2017.10.3390\/e19120656","DOI":"10.3390\/e19120656"},{"key":"2022050321464850722_j_popets-2019-0002_ref_023_w2aab3b7b2b1b6b1ab1ac23Aa","unstructured":"[23] S. Jana, D. Molnar, A. Moshchuk, A. Dunn, B. Livshits, H. J. Wang, and E. Ofek. Enabling Fine-Grained Permissions for Augmented Reality Applications With Recognizers. USENIX Security, 2013."},{"key":"2022050321464850722_j_popets-2019-0002_ref_024_w2aab3b7b2b1b6b1ab1ac24Aa","doi-asserted-by":"crossref","unstructured":"[24] S. Jana, A. Narayanan, and V. Shmatikov. A Scanner Darkly: Protecting User Privacy from Perceptual Applications. S & P, 2013.10.1109\/SP.2013.31","DOI":"10.1109\/SP.2013.31"},{"key":"2022050321464850722_j_popets-2019-0002_ref_025_w2aab3b7b2b1b6b1ab1ac25Aa","unstructured":"[25] J. Jia and N. Z. Gong. Attriguard: A practical defense against attribute inference attacks via adversarial machine learning. USENIX Security, 2018."},{"key":"2022050321464850722_j_popets-2019-0002_ref_026_w2aab3b7b2b1b6b1ab1ac26Aa","doi-asserted-by":"crossref","unstructured":"[26] J. Jung and M. Philipose. Courteous glass. UbiComp \u201814 Adjunct, 2014.10.1145\/2638728.2641711","DOI":"10.1145\/2638728.2641711"},{"key":"2022050321464850722_j_popets-2019-0002_ref_027_w2aab3b7b2b1b6b1ab1ac27Aa","unstructured":"[27] D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. ICLR, 2015."},{"key":"2022050321464850722_j_popets-2019-0002_ref_028_w2aab3b7b2b1b6b1ab1ac28Aa","unstructured":"[28] M. Korayem, R. Templeman, D. Chen, D. J. Crandall, and A. Kapadia. Screenavoider: Protecting computer screens from ubiquitous cameras. CoRR, 2014."},{"key":"2022050321464850722_j_popets-2019-0002_ref_029_w2aab3b7b2b1b6b1ab1ac29Aa","unstructured":"[29] A. Krizhevsky. Learning Multiple Layers of Features from Tiny Images. Master\u2019s thesis, 2009."},{"key":"2022050321464850722_j_popets-2019-0002_ref_030_w2aab3b7b2b1b6b1ab1ac30Aa","doi-asserted-by":"crossref","unstructured":"[30] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998.10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"2022050321464850722_j_popets-2019-0002_ref_031_w2aab3b7b2b1b6b1ab1ac31Aa","doi-asserted-by":"crossref","unstructured":"[31] Z. Liu, P. Luo, X. Wang, and X. Tang. Deep learning face attributes in the wild. ICCV, 2015.10.1109\/ICCV.2015.425","DOI":"10.1109\/ICCV.2015.425"},{"key":"2022050321464850722_j_popets-2019-0002_ref_032_w2aab3b7b2b1b6b1ab1ac32Aa","doi-asserted-by":"crossref","unstructured":"[32] M. Malekzadeh, R. G. Clegg, A. Cavallaro, and H. Haddadi. Protecting sensory data against sensitive inferences. EuroSys Workshop, 2018.10.1145\/3195258.3195260","DOI":"10.1145\/3195258.3195260"},{"key":"2022050321464850722_j_popets-2019-0002_ref_033_w2aab3b7b2b1b6b1ab1ac33Aa","doi-asserted-by":"crossref","unstructured":"[33] M. Malekzadeh, R. G. Clegg, and H. Haddadi. Replacement autoencoder: A privacy-preserving algorithm for sensory data analysis. IoTDI, 2018.10.1109\/IoTDI.2018.00025","DOI":"10.1109\/IoTDI.2018.00025"},{"key":"2022050321464850722_j_popets-2019-0002_ref_034_w2aab3b7b2b1b6b1ab1ac34Aa","unstructured":"[34] R. McPherson, R. Shokri, and V. Shmatikov. Defeating image obfuscation with deep learning. CoRR, 2016."},{"key":"2022050321464850722_j_popets-2019-0002_ref_035_w2aab3b7b2b1b6b1ab1ac35Aa","unstructured":"[35] S. J. Oh, R. Benenson, M. Fritz, and B. Schiele. Faceless person recognition; privacy implications in social media. ECCV, 2016."},{"key":"2022050321464850722_j_popets-2019-0002_ref_036_w2aab3b7b2b1b6b1ab1ac36Aa","unstructured":"[36] S. J. Oh, M. Fritz, and B. Schiele. Adversarial image perturbation for privacy protection - A game theory perspective. ICCV, 2017."},{"key":"2022050321464850722_j_popets-2019-0002_ref_037_w2aab3b7b2b1b6b1ab1ac37Aa","unstructured":"[37] W. Oleszkiewicz, T. Wlodarczyk, K. J. Piczak, T. Trzcinski, P. Kairouz, and R. Rajagopal. Siamese generative adversarial privatizer for biometric data. CVPR Workshops, 2018."},{"key":"2022050321464850722_j_popets-2019-0002_ref_038_w2aab3b7b2b1b6b1ab1ac38Aa","doi-asserted-by":"crossref","unstructured":"[38] T. Orekondy, M. Fritz, and B. Schiele. Connecting pixels to privacy and utility: Automatic redaction of private information in images. CVPR, 2018.10.1109\/CVPR.2018.00883","DOI":"10.1109\/CVPR.2018.00883"},{"key":"2022050321464850722_j_popets-2019-0002_ref_039_w2aab3b7b2b1b6b1ab1ac39Aa","unstructured":"[39] S. A. Ossia, A. S. Shamsabadi, A. Taheri, H. R. Rabiee, N. D. Lane, and H. Haddadi. A hybrid deep learning architecture for privacy-preserving mobile analytics. CoRR, 2017."},{"key":"2022050321464850722_j_popets-2019-0002_ref_040_w2aab3b7b2b1b6b1ab1ac40Aa","unstructured":"[40] K. Plarre, A. Raij, S. M. Hossain, A. A. Ali, M. Nakajima, M. Al\u2019absi, E. Ertin, T. Kamarck, S. Kumar, M. Scott, D. Siewiorek, A. Smailagic, and L. E. Wittmers. Continuous inference of psychological stress from sensory measurements collected in the natural environment. IPSN, 2011."},{"key":"2022050321464850722_j_popets-2019-0002_ref_041_w2aab3b7b2b1b6b1ab1ac41Aa","doi-asserted-by":"crossref","unstructured":"[41] N. Raval, A. Machanavajjhala, and L. P. Cox. Protecting visual secrets using adversarial nets. CVPR Workshops, 2017.10.1109\/CVPRW.2017.174","DOI":"10.1109\/CVPRW.2017.174"},{"key":"2022050321464850722_j_popets-2019-0002_ref_042_w2aab3b7b2b1b6b1ab1ac42Aa","doi-asserted-by":"crossref","unstructured":"[42] N. Raval, A. Srivastava, A. Razeen, K. Lebeck, A. Machanavajjhala, and L. P. Cox. What you mark is what apps see. MobiSys, 2016.10.1145\/2906388.2906405","DOI":"10.1145\/2906388.2906405"},{"key":"2022050321464850722_j_popets-2019-0002_ref_043_w2aab3b7b2b1b6b1ab1ac43Aa","unstructured":"[43] rovo89. Xposed framework. https:\/\/forum.xda-developers.com\/showthread.php?t=3034811."},{"key":"2022050321464850722_j_popets-2019-0002_ref_044_w2aab3b7b2b1b6b1ab1ac44Aa","doi-asserted-by":"crossref","unstructured":"[44] C. Schuldt, I. Laptev, and B. Caputo. Recognizing human actions: A local svm approach. ICPR, 2004.10.1109\/ICPR.2004.1334462","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"2022050321464850722_j_popets-2019-0002_ref_045_w2aab3b7b2b1b6b1ab1ac45Aa","doi-asserted-by":"crossref","unstructured":"[45] R. Shokri. Privacy Games: Optimal User-Centric Data Obfuscation. PETS, 2015.10.1515\/popets-2015-0024","DOI":"10.1515\/popets-2015-0024"},{"key":"2022050321464850722_j_popets-2019-0002_ref_046_w2aab3b7b2b1b6b1ab1ac46Aa","doi-asserted-by":"crossref","unstructured":"[46] S. Sonoda and N. Murata. Neural network with unbounded activations is universal approximator. ACHA, 2017.10.1016\/j.acha.2015.12.005","DOI":"10.1016\/j.acha.2015.12.005"},{"key":"2022050321464850722_j_popets-2019-0002_ref_047_w2aab3b7b2b1b6b1ab1ac47Aa","doi-asserted-by":"crossref","unstructured":"[47] R. Templeman, M. Korayem, D. Crandall, and A. Kapadia. PlaceAvoider: Steering first-person cameras away from sensitive spaces. NDSS, 2014.10.14722\/ndss.2014.23014","DOI":"10.14722\/ndss.2014.23014"},{"key":"2022050321464850722_j_popets-2019-0002_ref_048_w2aab3b7b2b1b6b1ab1ac48Aa","doi-asserted-by":"crossref","unstructured":"[48] A. Varshney and S. Puri. A survey on human personality identification on the basis of handwriting using ann. ICISC, 2017.10.1109\/ICISC.2017.8068634","DOI":"10.1109\/ICISC.2017.8068634"},{"key":"2022050321464850722_j_popets-2019-0002_ref_049_w2aab3b7b2b1b6b1ab1ac49Aa","doi-asserted-by":"crossref","unstructured":"[49] P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol. Extracting and composing robust features with denoising autoencoders. ICML, 2008.10.1145\/1390156.1390294","DOI":"10.1145\/1390156.1390294"},{"key":"2022050321464850722_j_popets-2019-0002_ref_050_w2aab3b7b2b1b6b1ab1ac50Aa","doi-asserted-by":"crossref","unstructured":"[50] C.-W. You, N. D. Lane, F. Chen, R. Wang, Z. Chen, T. J. Bao, M. Montes-de Oca, Y. Cheng, M. Lin, L. Torresani, and A. T. Campbell. Carsafe app: Alerting drowsy and distracted drivers using dual cameras on smartphones. MobiSys, 2013.10.1145\/2462456.2466711","DOI":"10.1145\/2462456.2466711"},{"key":"2022050321464850722_j_popets-2019-0002_ref_051_w2aab3b7b2b1b6b1ab1ac51Aa","doi-asserted-by":"crossref","unstructured":"[51] A. Zhan, M. Chang, Y. Chen, and A. Terzis. Accurate caloric expenditure of bicyclists using cellphones. SenSys, 2012.10.1145\/2426656.2426664","DOI":"10.1145\/2426656.2426664"},{"key":"2022050321464850722_j_popets-2019-0002_ref_052_w2aab3b7b2b1b6b1ab1ac52Aa","doi-asserted-by":"crossref","unstructured":"[52] X. Y. Zhang, G. S. Xie, C. L. Liu, and Y. Bengio. End-toend online writer identification with recurrent neural network. THMS, 2017.10.1109\/THMS.2016.2634921","DOI":"10.1109\/THMS.2016.2634921"}],"container-title":["Proceedings on Privacy Enhancing Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/content.sciendo.com\/view\/journals\/popets\/2019\/1\/article-p5.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciendo.com\/pdf\/10.2478\/popets-2019-0002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T16:30:15Z","timestamp":1658334615000},"score":1,"resource":{"primary":{"URL":"https:\/\/petsymposium.org\/popets\/2019\/popets-2019-0002.php"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,24]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,12,24]]},"published-print":{"date-parts":[[2019,1,1]]}},"alternative-id":["10.2478\/popets-2019-0002"],"URL":"https:\/\/doi.org\/10.2478\/popets-2019-0002","relation":{},"ISSN":["2299-0984"],"issn-type":[{"value":"2299-0984","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,24]]}}}