diff options
Diffstat (limited to 'biblio.bib')
| -rw-r--r-- | biblio.bib | 1125 |
1 files changed, 1124 insertions, 1 deletions
@@ -1,4 +1,113 @@ ######################"" +@misc{stateth, + titre={Statistiques ethniques}, + howpublished={\url{https://www.insee.fr/fr/information/2108548}}, + note={Dernier accès: 2024-09-19} +} + +@article{howard2000race, + title={Race, socioeconomic status, and cause-specific mortality}, + author={Howard, George and Anderson, Roger T and Russell, Gregory and Howard, Virginia J and Burke, Gregory L}, + journal={Annals of epidemiology}, + volume={10}, + number={4}, + pages={214--223}, + year={2000}, + publisher={Elsevier} +} +@article{williams1996race, + title={Race/ethnicity and socioeconomic status: measurement and methodological issues}, + author={Williams, David R}, + journal={International Journal of Health Services}, + volume={26}, + number={3}, + pages={483--505}, + year={1996}, + publisher={SAGE Publications Sage CA: Los Angeles, CA} +} + +@article{singler2017roko, + title={Roko's Basilisk or Pascal's? Thinking of Singularity Thought Experiments as Implicit Religion.}, + author={Singler, Beth}, + journal={Implicit Religion}, + volume={20}, + number={3}, + year={2017} +} + + +@incollection{green1972race, + title={Race, social status, and criminal arrest}, + author={Green, Edward R}, + booktitle={Readings in Criminology and Penology}, + pages={267--283}, + year={1972}, + publisher={Columbia University Press} +} +@article{walsh2007psychopathy, + title={Psychopathy and violent crime: A prospective study of the influence of socioeconomic status and ethnicity}, + author={Walsh, Zach and Kosson, David S}, + journal={Law and human behavior}, + volume={31}, + pages={209--229}, + year={2007}, + publisher={Springer} +} + + + + +@inproceedings{pelissier2024privacy, +author = {P\'{e}lissier, Samuel and Aalmoes, Jan and Mishra, Abhishek Kumar and Cunche, Mathieu and Roca, Vincent and Donsez, Didier}, +title = {Privacy-Preserving Pseudonyms for LoRaWAN}, +year = {2024}, +isbn = {9798400705823}, +publisher = {Association for Computing Machinery}, +address = {New York, NY, USA}, +url = {https://doi.org/10.1145/3643833.3656120}, +doi = {10.1145/3643833.3656120}, +abstract = {LoRaWAN, a widely deployed LPWAN protocol, raises privacy concerns due to metadata exposure, particularly concerning the exploitation of stable device identifiers. For the first time in literature, we propose two privacy-preserving pseudonym schemes tailored for LoRaWAN: resolvable pseudonyms and sequential pseudonyms. We extensively evaluate their performance and applicability through theoretical analysis and simulations based on a large-scale real-world dataset of 71 million messages. We conclude that sequential pseudonyms are the best solution.}, +booktitle = {Proceedings of the 17th ACM Conference on Security and Privacy in Wireless and Mobile Networks}, +pages = {14–19}, +numpages = {6}, +keywords = {iot, link-layer, lorawan, privacy, pseudonyms}, +location = {Seoul, Republic of Korea}, +series = {WiSec '24} +} + + + + +@inproceedings{Lebrun_2022, series={Middleware ’22}, + title={MixNN: protection of federated learning against inference attacks by mixing neural network layers}, + volume={2948}, + url={http://dx.doi.org/10.1145/3528535.3565240}, + DOI={10.1145/3528535.3565240}, + booktitle={Proceedings of the 23rd ACM/IFIP International Middleware Conference}, + publisher={ACM}, + author={Lebrun, Thomas and Boutet, Antoine and Aalmoes, Jan and Baud, Adrien}, + year={2022}, + month=nov, pages={135–147}, + collection={Middleware ’22} } + +@article{bergstra2015hyperopt, + title={Hyperopt: a python library for model selection and hyperparameter optimization}, + author={Bergstra, James and Komer, Brent and Eliasmith, Chris and Yamins, Dan and Cox, David D}, + journal={Computational Science \& Discovery}, + volume={8}, + number={1}, + pages={014008}, + year={2015}, + publisher={IOP Publishing} +} + +@misc{iris_53, + author = {Fisher, R. A.}, + title = {{Iris}}, + year = {1936}, + howpublished = {UCI Machine Learning Repository}, + note = {{DOI}: https://doi.org/10.24432/C56C76} +} @misc{chatgpt, title={ChatGPT}, howpublished={\url{https://openai.com/chatgpt/}}, @@ -503,7 +612,7 @@ publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3278721.3278779}, doi = {10.1145/3278721.3278779}, -abstract = {Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a framework for mitigating such biases by including a variable for the group of interest and simultaneously learning a predictor and an adversary. The input to the network X, here text or census data, produces a prediction Y, such as an analogy completion or income bracket, while the adversary tries to model a protected variable Z, here gender or zip code. The objective is to maximize the predictor's ability to predict Y while minimizing the adversary's ability to predict Z. Applied to analogy completion, this method results in accurate predictions that exhibit less evidence of stereotyping Z. When applied to a classification task using the UCI Adult (Census) Dataset, it results in a predictive model that does not lose much accuracy while achieving very close to equality of odds (Hardt, et al., 2016). The method is flexible and applicable to multiple definitions of fairness as well as a wide range of gradient-based learning models, including both regression and classification tasks.}, +abstract = {Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a framework for mitigating such biases by including a variable for the group of interest and simultaneously learning a predictor and an adversary. The input to the network X, here text or census data, produces a prediction Y, such as an analogy completion or income bracket, while the adversary tries to model a protected variable Z, here gender or zip code. The objective is to maximize the predictor's ability to predict Y while minimizing the adversary's ability to predict Z. Applied to analogy completion, this method results in accurate predictions that exhibit less evidence of stereotyping Z. When applied to a classification task using the UCI Adult (Census) Dataset, it results in a predictive model that does not lose much accuracy while achieving very close to equality of odds (Hardt, et al., 2016). The method is flexible and applicable to multiple definitions of fairness as well as a wide range of giradient-based learning models, including both regression and classification tasks.}, booktitle = {Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society}, pages = {335–340}, numpages = {6}, @@ -2879,3 +2988,1017 @@ number={9}, journal={Conference on Artificial Intelligence}, author={Ghosh, Bish publisher={Wiley Online Library} } + + +@misc{google_vision, + title = {Google vision }, + howpublished = {https://cloud.google.com/vision}, + note = {Accessed: 2021-05-27} +} +@article{ylc, + title="Gradient-Based Learning Applied to Document Recognition", + author="Y. LeCun, L. Bottou, Y. Bengio and P. Haffner", + journal="Proceedings of the IEEE", + volume="86", + number="11", + pages="2278-2324", + year="1998" +} +@misc{RGPD, + title="Le règlement général sur la protection des données", + howpublished="https://www.cnil.fr/fr/reglement-europeen-protection-donnees" +} +@misc{78-17, + title="Loi n° 78-17 du 6 janvier 1978 relative à l'informatique, aux fichiers et aux libertés", + howpublished="https://www.legifrance.gouv.fr/loda/id/LEGITEXT000006068624/2019-06-04/" +} +@misc{art, + title="Adversarial robustness toolbox", + howpublished="https://adversarial-robustness-toolbox.org/" +} +@misc{hardt2016equality, + title={Equality of Opportunity in Supervised Learning}, + author={Moritz Hardt and Eric Price and Nathan Srebro}, + year={2016}, + eprint={1610.02413}, + archivePrefix={arXiv}, + primaryClass={cs.LG} +} +@misc{chang2021privacy, + title={On the Privacy Risks of Algorithmic Fairness}, + author={Hongyan Chang and Reza Shokri}, + year={2021}, + eprint={2011.03731}, + archivePrefix={arXiv}, + primaryClass={stat.ML} +} +@misc{agarwal2018reductions, + title={A Reductions Approach to Fair Classification}, + author={Alekh Agarwal and Alina Beygelzimer and Miroslav Dudík and John Langford and Hanna Wallach}, + year={2018}, + eprint={1803.02453}, + archivePrefix={arXiv}, + primaryClass={cs.LG} +} +@misc{yeom, + title={Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting}, + author={Samuel Yeom and Irene Giacomelli and Matt Fredrikson and Somesh Jha}, + year={2018}, + eprint={1709.01604}, + archivePrefix={arXiv}, + primaryClass={cs.CR} +} +@article{saddlepointsolve, +title = {A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting}, +journal = {Journal of Computer and System Sciences}, +volume = {55}, +number = {1}, +pages = {119-139}, +year = {1997}, +issn = {0022-0000}, +doi = {https://doi.org/10.1006/jcss.1997.1504}, +url = {https://www.sciencedirect.com/science/article/pii/S002200009791504X}, +author = {Yoav Freund and Robert E Schapire}, +abstract = {In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone–Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in Rn. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.} +} +@misc{surveyfair, + title={A Survey on Bias and Fairness in Machine Learning}, + author={Ninareh Mehrabi and Fred Morstatter and Nripsuta Saxena and Kristina Lerman and Aram Galstyan}, + year={2019}, + eprint = {1908.09635} +} + +@inproceedings{10.1145/2020408.2020598, +author = {Cormode, Graham}, +title = {Personal Privacy vs Population Privacy: Learning to Attack Anonymization}, +year = {2011}, +booktitle = {KDD}, +pages = {1253–1261}, +} + +@inproceedings{abadi2016deep, + title={Deep learning with differential privacy}, + author={Abadi, Martin and Chu, Andy and Goodfellow, Ian and McMahan, H Brendan and Mironov, Ilya and Talwar, Kunal and Zhang, Li}, + booktitle={Proceedings of the 2016 ACM SIGSAC conference on computer and communications security}, + pages={308--318}, + year={2016} +} + + +@inproceedings{10.1145/3433210.3453095, +author = {Boutet, Antoine and Frindel, Carole and Gambs, S\'{e}bastien and Jourdan, Th\'{e}o and Ngueveu, Rosin Claude}, +title = {DySan: Dynamically Sanitizing Motion Sensor Data Against Sensitive Inferences through Adversarial Networks}, +year = {2021}, +booktitle = {Asia CCS}, +pages = {672–686}, +} + +@inproceedings {272298, +author = {Nishat Koti and Mahak Pancholi and Arpita Patra and Ajith Suresh}, +title = {{SWIFT}: Super-fast and Robust Privacy-Preserving Machine Learning}, +booktitle = {{USENIX} Security}, +year = {2021}, +publisher = {{USENIX} Association}, +} + +@misc{hunt2018chiron, + title={Chiron: Privacy-preserving Machine Learning as a Service}, + author={Tyler Hunt and Congzheng Song and Reza Shokri and Vitaly Shmatikov and Emmett Witchel}, + year={2018}, + eprint={1803.05961}, + archivePrefix={arXiv}, + primaryClass={cs.CR} +} + + +@misc{malekzadeh2021honestbutcurious, + title={Honest-but-Curious Nets: Sensitive Attributes of Private Inputs can be Secretly Coded into the Entropy of Classifiers' Outputs}, + author={Mohammad Malekzadeh and Anastasia Borovykh and Deniz Gündüz}, + year={2021}, + eprint={2105.12049}, + archivePrefix={arXiv}, + primaryClass={cs.LG} +} + +@InProceedings{pmlr-v130-vogel21a, + title = { Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints }, + author = {Vogel, Robin and Bellet, Aur{\'e}lien and Cl{\'e}men{\c{c}}on, Stephan}, + booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, + pages = {784--792}, + year = {2021}, + editor = {Banerjee, Arindam and Fukumizu, Kenji}, + volume = {130}, + series = {Proceedings of Machine Learning Research}, + month = {13--15 Apr}, +} + +@misc{chang2021privacy, + title={On the Privacy Risks of Algorithmic Fairness}, + author={Hongyan Chang and Reza Shokri}, + year={2021}, + eprint={2011.03731}, + archivePrefix={arXiv}, + primaryClass={stat.ML} +} + +@misc{fedsurvey, + title={Advances and Open Problems in Federated Learning}, + author={Peter Kairouz et al.}, + year={2019}, + eprint = {1912.04977} +} + +@techreport{ec2019ethics, + author = {High-Level Expert Group on AI}, + year={2019}, + title = {Ethics guidelines for trustworthy AI} +} + +@article{stealingtime, + author = {Vasisht Duddu and + Debasis Samanta and + D. Vijay Rao and + Valentina E. Balas}, + title = {Stealing Neural Networks via Timing Side Channels}, + year = {2018}, + eprint = {1812.11720} +} + +@misc{duddu2019quantifying, + title={Quantifying (Hyper) Parameter Leakage in Machine Learning}, + author={Vasisht Duddu and D. Vijay Rao}, + year={2019}, + eprint={1910.14409} +} + +@inproceedings{stealml, +author = {Tram\`{e}r, Florian and Zhang, Fan and Juels, Ari and Reiter, Michael K. and Ristenpart, Thomas}, +title = {Stealing Machine Learning Models via Prediction APIs}, +year = {2016}, +booktitle = {USENIX Security}, +pages = {601–618}, +} + + +@misc{duddu2021gecko, + title={GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning}, + author={Vasisht Duddu and Antoine Boutet and Virat Shejwalkar}, + year={2021}, + eprint={2010.00912}, + archivePrefix={arXiv}, + primaryClass={cs.CR} +} + +@misc{duddu2021quantifying, + title={Quantifying Privacy Leakage in Graph Embedding}, + author={Vasisht Duddu and Antoine Boutet and Virat Shejwalkar}, + year={2021}, + eprint={2010.00906}, + archivePrefix={arXiv}, + primaryClass={cs.CR} +} + +@inproceedings{NEURIPS2020_6b8b8e3b, + author = {Zhao, Han and Chi, Jianfeng and Tian, Yuan and Gordon, Geoffrey J}, + booktitle = {Advances in Neural Information Processing Systems}, + editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin}, + pages = {9485--9496}, + publisher = {Curran Associates, Inc.}, + title = {Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation}, + url = {https://proceedings.neurips.cc/paper/2020/file/6b8b8e3bd6ad94b985c1b1f1b7a94cb2-Paper.pdf}, + volume = {33}, + year = {2020} +} + +@inproceedings{10.1145/3319535.3363201, +author = {Jia, Jinyuan and Salem, Ahmed and Backes, Michael and Zhang, Yang and Gong, Neil Zhenqiang}, +title = {MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples}, +year = {2019}, +booktitle = {CCS}, +pages = {259–274} +} + + +@INPROCEEDINGS{meminf, +author={R. {Shokri} and M. {Stronati} and C. {Song} and V. {Shmatikov}}, +booktitle={SP}, +year = {2017}, +title={Membership Inference Attacks Against Machine Learning Models} +} + +@inproceedings{fedinversion, +author = {Hitaj, Briland and Ateniese, Giuseppe and Perez-Cruz, Fernando}, +title = {Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning}, +year = {2017}, +booktitle = {CCS}, +pages = {603–618} +} + + + + + +@INPROCEEDINGS{fedpriv2, +author={M. {Nasr} and R. {Shokri} and A. {Houmansadr}}, +booktitle={SP}, +year = {2019}, +title={Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning}, +pages={739-753}} + + +@inproceedings{fairprivatedata, +author = {Pujol, David and McKenna, Ryan and Kuppam, Satya and Hay, Michael and Machanavajjhala, Ashwin and Miklau, Gerome}, +title = {Fair Decision Making Using Privacy-Protected Data}, +year = {2020}, +booktitle = {FAT*}, +pages = {189–199}, +} + +@inproceedings{compatibility, +author = {Cummings, Rachel and Gupta, Varun and Kimpara, Dhamma and Morgenstern, Jamie}, +title = {On the Compatibility of Privacy and Fairness}, +year = {2019}, +booktitle = {UMAP}, +pages = {309–315} +} + +@inproceedings{Song2020Overlearning, +title={Overlearning Reveals Sensitive Attributes}, +author={Congzheng Song and Vitaly Shmatikov}, +booktitle={International Conference on Learning Representations}, +year={2020} +} + +@ARTICLE{8515092, +author={S. A. {Osia} and A. {Taheri} and A. S. {Shamsabadi} and K. {Katevas} and H. {Haddadi} and H. R. {Rabiee}}, +journal={IEEE Transactions on Knowledge and Data Engineering}, +title={Deep Private-Feature Extraction}, +year={2020}, +volume={32}, +number={1}, +pages={54-66},} + + +@misc{removedispimpactdpsgd, +title={Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy}, +author={Depeng Xu and Wei Du and Xintao Wu}, +year={2020}, +eprint = {2003.03699}, +} + +@article{incompatibility, +title={Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy}, +author={Rastegarpanah, Bashir and Crovella, Mark and Gummadi, Krishna P}, +eprint = {2005.09209}, +year={2020} +} + +@article{fairvrobust, +author = {Hongyan Chang and Ta Duy Nguyen and Sasi Kumar Murakonda and Ehsan Kazemi and Reza Shokri}, +title = {On Adversarial Bias and the Robustness of Fair Machine Learning}, +year = {2020}, +eprint = {2006.08669} +} + +@article{dispvuln, +author = {Mohammad Yaghini and Bogdan Kulynych and Carmela Troncoso}, +title = {Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning}, +year = {2019}, +eprint = {1906.00389} +} + +@incollection{dpaccdisp, +title = {Differential Privacy Has Disparate Impact on Model Accuracy}, +author = {Bagdasaryan, Eugene and Poursaeed, Omid and Shmatikov, Vitaly}, +booktitle = {NIPS}, +pages = {15479--15488}, +year = {2019}} + +@misc{dpmeminf, +title={Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack}, +author={Bo Zhang and Ruotong Yu and Haipei Sun and Yanying Li and Jun Xu and Hui Wang}, +year={2020}, +eprint={2001.08855} +} + + + + + + + + + +@article{advfair, + author = {Alex Beutel and Jilin Chen and Zhe Zhao and Ed H. Chi}, + title = {Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations}, + year = {2017}, + eprint = {1707.00075} +} + +@article{propinf, + title={Dataset-Level Attribute Leakage in Collaborative Learning}, + author={Zhang, Wanrong and Tople, Shruti and Ohrimenko, Olga}, + journal={arXiv:2006.07267}, + year={2020} +} + +@article{propinf2, +author = {Ateniese, Giuseppe and Mancini, Luigi V. and Spognardi, Angelo and Villani, Antonio and Vitali, Domenico and Felici, Giovanni}, +title = {Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers}, +year = {2015}, +volume = {10}, +number = {3}, +journal = {Int. J. Secur. Netw.}, +month = sep, +pages = {137–150} +} + +@inproceedings{10.5555/3042817.3042973, +author = {Zemel, Richard and Wu, Yu and Swersky, Kevin and Pitassi, Toniann and Dwork, Cynthia}, +title = {Learning Fair Representations}, +year = {2013}, +booktitle = {ICML} +} + +@article{10.5555/3122009.3208010, +author = {Hamm, Jihun}, +title = {Minimax Filter: Learning to Preserve Privacy from Inference Attacks}, +year = {2017}, +volume = {18}, +number = {1}, +journal = {J. Mach. Learn. Res.}, +month = jan, +pages = {4704–4734} +} + +@inproceedings{10.5555/3327546.3327583, +author = {Moyer, Daniel and Gao, Shuyang and Brekelmans, Rob and Steeg, Greg Ver and Galstyan, Aram}, +title = {Invariant Representations without Adversarial Training}, +year = {2018}, +booktitle = {NIPS} +} + +@inproceedings{10.5555/3294771.3294827, +author = {Xie, Qizhe and Dai, Zihang and Du, Yulun and Hovy, Eduard and Neubig, Graham}, +title = {Controllable Invariance through Adversarial Feature Learning}, +year = {2017}, +booktitle = {NIPS} +} + +@InProceedings{pmlr-v80-madras18a, + title = {Learning Adversarially Fair and Transferable Representations}, + author = {Madras, David and Creager, Elliot and Pitassi, Toniann and Zemel, Richard}, + pages = {3384--3393}, + year = {2018}, + volume = {80}, + series = {Proceedings of Machine Learning Research}, +} + +@inproceedings{censoringadv, +title = "Censoring Representations with an Adversary", +author = "Harrison Edwards and Amos Storkey", +year = "2016", +booktitle = “ICLR”} + + + + + + +@inproceedings{propinf3, +author = {Ganju, Karan and Wang, Qi and Yang, Wei and Gunter, Carl A. and Borisov, Nikita}, +title = {Property Inference Attacks on Fully Connected Neural Networks Using Permutation Invariant Representations}, +year = {2018}, +booktitle = {CCS}, +pages = {619–633} +} + +@inproceedings {whiteboxmeminf, +author = {Klas Leino and Matt Fredrikson}, +title = {Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference}, +booktitle = {USENIX Security}, +year = {2020}, +pages = {1605--1622} +} + + +@inproceedings{modelinv, +author = {Fredrikson, Matt and Jha, Somesh and Ristenpart, Thomas}, +title = {Model Inversion Attacks That Exploit Confidence Information and Basic Countermeasures}, +year = {2015}, +booktitle = {CCS}, +pages = {1322–1333} +} + +@inproceedings{advtrain, +author = {Louppe, Gilles and Kagan, Michael and Cranmer, Kyle}, +title = {Learning to Pivot with Adversarial Networks}, +year = {2017}, +booktitle = {NeurIPS}, +pages = {982–991} +} + +@inproceedings {attriguard, +author = {Jinyuan Jia and Neil Zhenqiang Gong}, +title = {AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning}, +booktitle = {USENIX Security}, +year = {2018}, +pages = {513--529}, +} + + + + + + + + +@INPROCEEDINGS{fedinference, +author={L. {Melis} and C. {Song} and E. {De Cristofaro} and V. {Shmatikov}}, +booktitle={SP}, +title={Exploiting Unintended Feature Leakage in Collaborative Learning}, +year={2019}, +pages={691-706}} + +@article{fairmetric, +author = {Muhammad Bilal Zafar and Isabel Valera and Manuel Gomez-Rodriguez and Krishna P. Gummadi}, +title = {Fairness Constraints: A Flexible Approach for Fair Classification}, +journal = {Journal of Machine Learning Research}, +year = {2019}, +volume = {20}, +number = {75}, +pages = {1-42} +} + +@inproceedings{fairmetric2, +author = {Hardt, Moritz and Price, Eric and Srebro, Nathan}, +title = {Equality of Opportunity in Supervised Learning}, +year = {2016}, +booktitle = {NIPS}, +pages = {3323–3331} +} + + +@misc{yeom, + title={Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting}, + author={Samuel Yeom and Irene Giacomelli and Matt Fredrikson and Somesh Jha}, + year={2018}, + booktitle = {CSF} +} + +@inproceedings{Mahajan2020DoesLS, + title={Does Learning Stable Features Provide Privacy Benefits for Machine Learning Models?}, + author={Divyat Mahajan, Shruti Tople, Amit Sharma}, + booktitle = {NeurIPS PPML Workshop}, + year={2020} +} + +@msic{advrobtool, + title={Adversarial robustness toolbox}, + howpublished={\url{https://adversarial-robustness-toolbox.org}}, + note = {Accessed: 2021-06-22} +} + + +@inproceedings{debiase, +author = {Zhang, Brian Hu and Lemoine, Blake and Mitchell, Margaret}, +title = {Mitigating Unwanted Biases with Adversarial Learning}, +year = {2018}, +booktitle = {AIES}, +pages = {335–340}, +location = {New Orleans, LA, USA} +} + + +@article{preprocessing, +author = {Kamiran, Faisal and Calders, Toon}, +year = {2011}, +month = {10}, +pages = {}, +title = {Data Pre-Processing Techniques for Classification without Discrimination}, +volume = {33}, +journal = {Knowledge and Information Systems}, +doi = {10.1007/s10115-011-0463-8} +} + + +@InProceedings{reductions, + title = {A Reductions Approach to Fair Classification}, + author = {Agarwal, Alekh and Beygelzimer, Alina and Dudik, Miroslav and Langford, John and Wallach, Hanna}, + booktitle = {Proceedings of the 35th International Conference on Machine Learning}, + pages = {60--69}, + year = {2018}, + editor = {Dy, Jennifer and Krause, Andreas}, + volume = {80}, + series = {Proceedings of Machine Learning Research}, + month = {10--15 Jul}, + publisher = {PMLR}, + pdf = {http://proceedings.mlr.press/v80/agarwal18a/agarwal18a.pdf}, + url = {http://proceedings.mlr.press/v80/agarwal18a.html}, + abstract = {We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach encompasses many other previously studied definitions as special cases. The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. We introduce two reductions that work for any representation of the cost-sensitive classifier and compare favorably to prior baselines on a variety of data sets, while overcoming several of their disadvantages.} +} +@article{recomender, + title={Data Poisoning Attacks to Deep Learning Based Recommender Systems}, + ISBN={1891562665}, + url={http://dx.doi.org/10.14722/ndss.2021.24525}, + DOI={10.14722/ndss.2021.24525}, + journal={Proceedings 2021 Network and Distributed System Security Symposium}, + publisher={Internet Society}, + author={Huang, Hai and Mu, Jiaming and Gong, Neil Zhenqiang and Li, Qi and Liu, Bin and Xu, Mingwei}, + year={2021} +} + + +@book{ortiz2015smartphone, + title={Smartphone-based human activity recognition}, + author={Reyes-Ortiz, J. L.}, + year={2015}, + publisher={Springer} +} + +% Encoding: UTF-8 + +@inproceedings{DBLP:conf/srds/ContiuVPPFR19, + author = {Stefan Contiu and + S{\'{e}}bastien Vaucher and + Rafael Pires and + Marcelo Pasin and + Pascal Felber and + Laurent R{\'{e}}veill{\`{e}}re}, + title = {Anonymous and Confidential File Sharing over Untrusted Clouds}, + booktitle = {SRDS}, + pages = {21--31}, + year = {2019}, +} + +@article{10.1504/IJSN.2015.071829, +author = {Ateniese, Giuseppe and Mancini, Luigi V. and Spognardi, Angelo and Villani, Antonio and Vitali, Domenico and Felici, Giovanni}, +title = {Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers}, +year = {2015}, +volume = {10}, +number = {3}, +journal = {Int. J. Secur. Netw.}, +month = sep, +pages = {137–150}, +numpages = {14} +} + + + +@article{salem2018mlleaks, + title={ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models}, + author={Ahmed Salem and Yang Zhang and Mathias Humbert and Pascal Berrang and Mario Fritz and Michael Backes}, + year={2018}, + journal={arXiv:1806.01246}, +} + +@inproceedings{DBLP:conf/middleware/SilvaMCNRR19, + author = {Simon Da Silva and + Sonia Ben Mokhtar and + Stefan Contiu and + Daniel N{\'{e}}gru and + Laurent R{\'{e}}veill{\`{e}}re and + Etienne Rivi{\`{e}}re}, + title = {PrivaTube: Privacy-Preserving Edge-Assisted Video Streaming}, + booktitle = {Middleware}, + pages = {189--201}, + year = {2019}, +} + +@inproceedings{duriakova2019pdmfrec, + title={{PDMFRec}: a decentralised matrix factorisation with tunable user-centric privacy}, + author={Duriakova, Erika and Tragos, Elias Z and Smyth, Barry and Hurley, Neil and Pe{\~n}a, Francisco J and Symeonidis, Panagiotis and Geraci, James and Lawlor, Aonghus}, + booktitle={RecSys}, + pages={457--461}, + year={2019}, +} + +@article{shin2018privacy, + title={Privacy enhanced matrix factorization for recommendation with local differential privacy}, + author={Shin, Hyejin and Kim, Sungwook and Shin, Junbum and Xiao, Xiaokui}, + journal={TKDE}, + volume={30}, + number={9}, + pages={1770--1782}, + year={2018}, +} +@inproceedings{dwork2008differential, + title={Differential privacy: A survey of results}, + author={Dwork, Cynthia}, + booktitle={TAMC}, + pages={1--19}, + year={2008}, +} + +@inproceedings{wang2019cryptorec, + title={Novel Collaborative Filtering Recommender Friendly to Privacy Protection}, + author={Wang, Jun and Tang, Qiang and Arriaga, Afonso and Ryan, Peter YA}, + booktitle={IJCAI}, + year={2019} +} +@inproceedings{narayanan2008robust, + title={Robust de-anonymization of large datasets (how to break anonymity of the Netflix prize dataset)}, + author={Narayanan, Arvind and Shmatikov, Vitaly}, + booktitle={S\&P}, + year={2008} +} + +@article{zhang2020datasetlevel, + title={Dataset-Level Attribute Leakage in Collaborative Learning}, + author={Wanrong Zhang and Shruti Tople and Olga Ohrimenko}, + year={2020}, + journal={arXiv:2006.07267} +} + +@inproceedings{calandrino2011you, + title={"You might also like:" Privacy risks of collaborative filtering}, + author={Calandrino, Joseph A and Kilzer, Ann and Narayanan, Arvind and Felten, Edward W and Shmatikov, Vitaly}, + booktitle={S\&P}, + pages={231--246}, + year={2011}, +} +@article{mousa2015trust, + title={Trust management and reputation systems in mobile participatory sensing applications: A survey}, + author={Mousa, Hayam and Mokhtar, Sonia Ben and Hasan, Omar and Younes, Osama and Hadhoud, Mohiy and Brunie, Lionel}, + journal={Computer Networks}, + volume={90}, + pages={49--73}, + year={2015}, +} +@inproceedings{butin2015guide, + title={A guide to end-to-end privacy accountability}, + author={Butin, Denis and Le M{\'e}tayer, Daniel}, + booktitle={TEchnical and LEgal aspects of data pRivacy and SEcurity}, + pages={20--25}, + year={2015}, +} +@article{gunes2014shilling, + title={Shilling attacks against recommender systems: a comprehensive survey}, + author={Gunes, Ihsan and Kaleli, Cihan and Bilge, Alper and Polat, Huseyin}, + journal={Artificial Intelligence Review}, + volume={42}, + number={4}, + pages={767--799}, + year={2014}, +} + +@inproceedings{boutet2018collaborative, + title={Collaborative filtering under a sybil attack: Similarity metrics do matter!}, + author={Boutet, Antoine and De Moor, Florestant and Frey, Davide and Guerraoui, Rachid and Kermarrec, Anne-Marie and Rault, Antoine}, + booktitle={DSN}, + pages={466--477}, + year={2018}, +} +@article{boutet2016privacy, + title={Privacy-preserving distributed collaborative filtering}, + author={Boutet, Antoine and Frey, Davide and Guerraoui, Rachid and J{\'e}gou, Arnaud and Kermarrec, Anne-Marie}, + journal={Computing}, + volume={98}, + number={8}, + pages={827--846}, + year={2016}, +} +@inproceedings{gan2020enhancing, + title={Enhancing recommendation diversity using determinantal point processes on knowledge graphs}, + author={Gan, Lu and Nurbakova, Diana and Laporte, L{\'e}a and Calabretto, Sylvie}, + booktitle={SIGIR}, + pages={2001--2004}, + year={2020} +} +@inproceedings{diarra2014fullreview, + title={Fullreview: Practical accountability in presence of selfish nodes}, + author={Diarra, Amadou and Mokhtar, Sonia Ben and Aublin, Pierre-Louis and Qu{\'e}ma, Vivien}, + booktitle={SRDS}, + pages={271--280}, + year={2014}, +} + +@inproceedings{contiu2018ibbe, + title={IBBE-SGX: Cryptographic group access control using trusted execution environments}, + author={Contiu, Stefan and Pires, Rafael and Vaucher, S{\'e}bastien and Pasin, Marcelo and Felber, Pascal and R{\'e}veill{\`e}re, Laurent}, + booktitle={DSN}, + pages={207--218}, + year={2018}, +} + +@article{damaskinos2020fleet, + title={FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction}, + author={Damaskinos, Georgios and Guerraoui, Rachid and Kermarrec, Anne-Marie and Nitu, Vlad and Patra, Rhicheek and Taiani, Francois}, + journal={arXiv:2006.07273}, + year={2020} +} + +@inproceedings{jiang2020detection, + title={On the Detection of Shilling Attacks in Federated Collaborative Filtering}, + author={Jiang, Yangfan and Zhou, Yipeng and Wu, Di and Li, Chao and Wang, Yan}, + booktitle={SRDS}, + pages={185--194}, + year={2020}, +} + +@article{bonawitz2016practical, + title={Practical secure aggregation for federated learning on user-held data}, + author={Bonawitz, Keith and Ivanov, Vladimir and Kreuter, Ben and Marcedone, Antonio and McMahan, H Brendan and Patel, Sarvar and Ramage, Daniel and Segal, Aaron and Seth, Karn}, + journal={arXiv:1611.04482}, + year={2016} +} + + + +@article{wang2020attack, + title={Attack of the tails: Yes, you really can backdoor federated learning}, + author={Wang, Hongyi and Sreenivasan, Kartik and Rajput, Shashank and Vishwakarma, Harit and Agarwal, Saurabh and Sohn, Jy-yong and Lee, Kangwook and Papailiopoulos, Dimitris}, + journal={arXiv:2007.05084}, + year={2020} +} + +@inproceedings{muhammad2020fedfast, + title={FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems}, + author={Muhammad, Khalil and Wang, Qinqin and O'Reilly-Morgan, Diarmuid and Tragos, Elias and Smyth, Barry and Hurley, Neil and Geraci, James and Lawlor, Aonghus}, + booktitle={SIGKDD}, + pages={1234--1242}, + year={2020} +} +@article{zhang2018explainable, + title={Explainable recommendation: A survey and new perspectives}, + author={Zhang, Yongfeng and Chen, Xu}, + volume = {14}, + journal = {Foundations and Trends in Information Retrieval}, + number = {1}, + pages = {1-101}, + year={2020} +} + +@inproceedings{fleder2007recommender, + title={Recommender systems and their impact on sales diversity}, + author={Fleder, Daniel M and Hosanagar, Kartik}, + booktitle={Conference on Electronic Commerce}, + pages={192--199}, + year={2007}, +} + +@inproceedings{garcin2014offline, + title={Offline and online evaluation of news recommender systems at {swissinfo.ch}}, + author={Garcin, Florent and Faltings, Boi and Donatsch, Olivier and Alazzawi, Ayar and Bruttin, Christophe and Huber, Amr}, + booktitle={RecSys}, + pages={169--176}, + year={2014}, +} + +@inproceedings{ge2010beyond, + title={Beyond accuracy: evaluating recommender systems by coverage and serendipity}, + author={Ge, Mouzhi and Delgado-Battenfeld, Carla and Jannach, Dietmar}, + booktitle={RecSys}, + pages={257--260}, + year={2010}, +} + +@article{bobadilla2013recommender, + title={Recommender systems survey}, + author={Bobadilla, Jes{\'u}s and Ortega, Fernando and Hernando, Antonio and Guti{\'e}rrez, Abraham}, + journal={Knowledge-Based Systems}, + volume={46}, + __pages={109--132}, + year={2013}, +} + +@inproceedings{tan2020federated, + title={A Federated Recommender System for Online Services}, + author={Tan, Ben and Liu, Bo and Zheng, Vincent and Yang, Qiang}, + booktitle={RecSys}, + pages={579--581}, + year={2020} +} + +@inproceedings{gao2020dplcf, + title={DPLCF: Differentially Private Local Collaborative Filtering}, + author={Gao, Chen and Huang, Chao and Lin, Dongsheng and Jin, Depeng and Li, Yong}, + booktitle={SIGIR}, + pages={961--970}, + year={2020} +} + +@inproceedings{guerraoui2017know, + title={I know nothing about you but here is what you might like}, + author={Guerraoui, Rachid and Kermarrec, Anne-Marie and Patra, Rhicheek and Valiyev, Mahammad and Wang, Jingjing}, + booktitle={DSN}, + pages={439--450}, + year={2017}, +} + + +@article{MovieLens, + author = {Harper, F. Maxwell and Konstan, Joseph A.}, + title = {The MovieLens Datasets: History and Context}, + journal = {TIIS}, + volume={5}, + number={4}, + year={2016}, +} + +@incollection{burke2015robust, + title={Robust collaborative recommendation}, + author={Burke, Robin and O’Mahony, Michael P and Hurley, Neil J}, + booktitle={Recommender systems handbook}, + pages={961--995}, + year={2015}, +} + +@inproceedings{dasilva2019privatube, + title={PrivaTube: Privacy-Preserving Edge-Assisted Video Streaming}, + author={Da Silva, Simon and Ben Mokhtar, Sonia and Contiu, Stefan and N{\'e}gru, Daniel and R{\'e}veill{\`e}re, Laurent and Rivi{\`e}re, Etienne}, + booktitle={Middleware}, + year={2019} +} + +@article{haeberlen2007peerreview, + title={PeerReview: Practical accountability for distributed systems}, + author={Haeberlen, Andreas and Kouznetsov, Petr and Druschel, Peter}, + journal={SIGOPS operating systems review}, + volume={41}, + number={6}, + year={2007}, +} + +@inproceedings{decouchant2019p3ls, + title={P3LS: Plausible Deniability for Practical Privacy-Preserving Live Streaming}, + author={Decouchant, J{\'e}r{\'e}mie and Boutet, Antoine and Yu, Jiangshan and Esteves-Verissimo, Paulo}, + booktitle={SRDS}, + year={2019} +} + + +@article{georgopoulos2014distributed, + title={Distributed machine learning in networks by consensus}, + author={Georgopoulos, Leonidas and Hasler, Martin}, + journal={Neurocomputing}, + volume={124}, + pages={2--12}, + year={2014}, +} + +@article{fierimonte2016fully, + title={Fully decentralized semi-supervised learning via privacy-preserving matrix completion}, + author={Fierimonte, Roberto and Scardapane, Simone and Uncini, Aurelio and Panella, Massimo}, + journal={Transactions on neural networks and learning systems}, + volume={28}, + number={11}, + pages={2699--2711}, + year={2016}, +} + + +@inproceedings{ling2012decentralized, + title={Decentralized low-rank matrix completion}, + author={Ling, Qing and Xu, Yangyang and Yin, Wotao and Wen, Zaiwen}, + booktitle={ICASSP}, + pages={2925--2928}, + year={2012}, +} + +@inproceedings{chang2014factorized, + title={Factorized similarity learning in networks}, + author={Chang, Shiyu and Qi, Guo-Jun and Aggarwal, Charu C and Zhou, Jiayu and Wang, Meng and Huang, Thomas S}, + booktitle={ICDM}, + pages={60--69}, + year={2014}, +} + +@inproceedings{boutet:hal-00769291, + TITLE = {{WhatsUp Decentralized Instant News Recommender}}, + AUTHOR = {Boutet, Antoine and Frey, Davide and Guerraoui, Rachid and J{\'e}gou, Arnaud and Kermarrec, Anne-Marie}, + BOOKTITLE = {IPDPS}, + YEAR = {2013}, +} + + +@article{koren2009matrix, + title={Matrix factorization techniques for recommender systems}, + author={Koren, Yehuda and Bell, Robert and Volinsky, Chris}, + journal={Computer}, + volume={42}, + number={8}, + pages={30--37}, + year={2009}, +} + + +@misc{eachmovie, + title={EachMovie collaborative filtering data set}, + howpublished={https://www.cs.cmu.edu/~lebanon/IR-lab/data.html} +} + +@Book{Pearl1988, + title = {\href{https://dl.acm.org/citation.cfm?id=52121}{Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference}}, + publisher = {Morgan Kaufmann}, + year = {1988}, + author = {Pearl, J.}, + owner = {Vincent}, + timestamp = {2018.03.25}, +} + +@Article{Zadeh1965, + author = {Zadeh, L. A.}, + title = {\href{https://doi.org/10.1016/S0019-9958(65)90241-X}{Fuzzy sets}}, + journal = {Information and Control}, + year = {1965}, + volume = {8}, + number = {3}, + pages = {338-353}, + owner = {Vincent}, + timestamp = {2018.03.25}, +} + +@InProceedings{Agrawal1993, + author = {Agrawal, R. and Imieliński, T. and Swami, A.}, + title = {\href{https://doi.org/10.1145/170036.170072}{Mining association rules between sets of items in large databases}}, + booktitle = {ACM SIGMOD International Conference on Management of data}, + year = {1993}, + pages = {207-216}, + owner = {Vincent}, + timestamp = {2018.03.25}, +} + +@misc{ppstream, + title={PPStream}, + howpublished={http://www.ppstream.com} +} + +@inproceedings{datta2015automated, + title={Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination}, + author={Amit Datta and Michael Carl Tschantz and Anupam Datta}, + year={2015}, + booktitle={PETS}, +} + +@inproceedings{barkan2020explainable, + title={Explainable recommendations via attentive multi-persona collaborative filtering}, + author={Barkan, Oren and Fuchs, Yonatan and Caciularu, Avi and Koenigstein, Noam}, + booktitle={RecSys}, + pages={468--473}, + year={2020} +} + +@inproceedings{Afchar_2020, + title={Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction}, + booktitle={RecSys}, + author={Afchar, Darius and Hennequin, Romain}, + year={2020}, +} + +@inproceedings{Schnabel2020TheIO, + title={The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation}, + author={Tobias Schnabel and Saleema Amershi and P. Bennett and P. Bailey and T. Joachims}} + +@BOOK{Bourrigan2021-dd, + title = "Maths {MPSI-MP2I}: tout-en-un", + author = "Bourrigan, Maxime and Delsinne, Emmanuel and Gentric, Yoann and + Lussier, Fran{\c c}ois and Mullaert, Chlo{\'e} and ), Serge + Nicolas (math{\'e}maticien) and Nougayr{\`e}de, Jean and + T{\^e}te, Claire and Volcker, Michel", + year = 2021, + language = "fr" +} + + |