{"type":"ScholarlyArticle","title":"Privacy-Preserving Obfuscation of Critical Infrastructure Networks","authors":[{"name":"Ferdinando Fioretto","slug":"ferdinando-fioretto","given":"Ferdinando","family":"Fioretto","affiliation":"Georgia Institute of Technology; Syracuse University"},{"name":"Terrence W.K. Mak","slug":"terrence-w-k-mak","given":"Terrence W.K.","family":"Mak","affiliation":"Georgia Institute of Technology"},{"name":"Pascal Van Hentenryck","slug":"pascal-van-hentenryck","given":"Pascal","family":"Van Hentenryck","affiliation":"Georgia Institute of Technology"}],"abstract":"The paper studies how to release data about a critical infrastructure network (e.g., a power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, while preserving the realism of the network. It proposes a novel obfuscation mechanism that combines several privacy-preserving building blocks with a bi-level optimization model to significantly improve accuracy. The obfuscation is evaluated for both realism and privacy properties on real energy and transportation networks. Experimental results show the obfuscation mechanism substantially reduces the potential damage of an attack exploiting the released data to harm the real network.","doi":"10.24963/ijcai.2019/152","url":"https://ijcai.org/proceedings/2019/152","pdf":"https://ijcai.org/proceedings/2019/0152.pdf","markdown":"https://ijcai.org/proceedings/2019/152.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/152","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Constraints and SAT","track":"Main track","number":152,"pages":{"first":1086,"last":1092},"keywords":["Constraints and SAT: Constraints: Applications","Multidisciplinary Topics and Applications: Security and Privacy"],"videos":[],"references":[{"position":1,"raw":"[Aiyoshi and Shimizu, 1984] Eitaro Aiyoshi and Kiyotaka Shimizu. A solution method for the static con- strained stackelberg problem via penalty method. AC, 29(12):1111-1114, 1984.","title":"Eitaro Aiyoshi and Kiyotaka Shimizu. A solution method for the static constrained stackelberg problem via penalty method","authors":"Shimizu Aiyoshi","year":"1984","venue":"AC","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Andrés et al., 2013] Miguel Andrés, Nicolás Bordenabe, Konstantinos Chatzikokolakis, and Catuscia Palamidessi. Geo-indistinguishability: Differential privacy for location- based systems. In CCS, pages 901-914, 2013.","title":"Geo-indistinguishability: Differential privacy for locationbased systems","authors":"Miguel Andrés, Nicolás Bordenabe, Konstantinos Chatzikokolakis, Catuscia Palamidessi","year":"2013","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Blocki et al., 2013] Jeremiah Blocki, Avrim Blum, Anupam Datta, and Or Sheffet. Differentially private data analysis of social networks via restricted sensitivity. In ITCS, pages 87-96, 2013.","title":"Differentially private data analysis of social networks via restricted sensitivity","authors":"Blocki","year":"2013","venue":"ITCS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chatzikokolakis et al., 2013] Konstantinos Chatzikoko- lakis, Miguel E Andrés, Nicolás Emilio Bordenabe, and Catuscia Palamidessi. Broadening the scope of differential privacy using metrics. In PETS, pages 82-102, 2013.","title":"Broadening the scope of differential privacy using metrics","authors":"Konstantinos Chatzikokolakis, Miguel E Andrés, Nicolás Emilio Bordenabe, Catuscia Palamidessi","year":"2013","venue":"PETS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Coffrin et al., 2014] Carleton Coffrin, Dan Gordon, and Paul Scott. Nesta, the NICTA energy system test case archive. CoRR, abs/1411.0359, 2014.","title":"Nesta, the NICTA energy system test case archive","authors":"Coffrin","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Coffrin et al., 2018] Carleton Coffrin, Russell Bent, Kaarthik Sundar, Yeesian Ng, and Miles Lubin. Pow- ermodels.jl: An open-source framework for exploring power flow formulations. In PSCC, pages 1-8, June 2018.","title":"Powermodels.jl: An open-source framework for exploring power flow formulations","authors":"Coffrin","year":"2018","venue":"PSCC","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dwork and Roth, 2013] Cynthia Dwork and Aaron Roth. The algorithmic foundations of differential privacy. Theo- retical Computer Science, 9(3-4):211-407, 2013.","title":"The algorithmic foundations of differential privacy","authors":"Roth ; Dwork, Cynthia Dwork, Aaron Roth","year":"2013","venue":"Theoretical Computer Science","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dwork et al., 2006] Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sensitivity in private data analysis. In TCC, volume 3876, pages 265-284, 2006.","title":"Calibrating noise to sensitivity in private data analysis","authors":"Cynthia Dwork, Frank Mcsherry, Kobbi Nissim, Adam Smith","year":"2006","venue":"TCC","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fioretto and Van Hentenryck, 2018] Ferdinando Fioretto and Pascal Van Hentenryck. Constrained-based differen- tial privacy: Releasing optimal power flow benchmarks privately. In CPAIOR, pages 215-231, 2018.","title":"Constrained-based differential privacy: Releasing optimal power flow benchmarks privately","authors":"Van Fioretto, Ferdinando Hentenryck, Pascal Fioretto, Van Hentenryck","year":"2018","venue":"CPAIOR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fioretto et al., 2018] Ferdinando Fioretto, Chansoo Lee, and Pascal Van Hentenryck. Constrained-based differen- tial privacy for private mobility. In AAMAS, pages 1405- 1413, 2018.","title":"Constrained-based differential privacy for private mobility","authors":"Ferdinando Fioretto, Chansoo Lee, Pascal Van Hentenryck","year":"2018","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fioretto et al., 2019] Ferdinando Fioretto, Terrence W. K. Mak, and Pascal Van Hentenryck. Privacy-preserving ob- fuscation of critical infrastructure networks (extended ver- sion). CoRR, abs/1905.09778, 2019.","title":"Privacy-preserving obfuscation of critical infrastructure networks (extended version)","authors":"Ferdinando Fioretto, Terrence W K Mak, Pascal Van Hentenryck","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ghafouri et al., 2018] Amin Ghafouri, Yevgeniy Vorobey- chik, and Xenofon D. Koutsoukos. Adversarial regression for detecting attacks in cyber-physical systems. In IJCAI, pages 3769-3775, 2018.","title":"Adversarial regression for detecting attacks in cyber-physical systems","authors":"Amin Ghafouri, Yevgeniy Vorobeychik, Xenofon D Koutsoukos","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/524"},{"position":13,"raw":"[Hansen et al., 1992] Pierre Hansen, Brigitte Jaumard, and Gilles Savard. New branch-and-bound rules for linear bilevel programming. SIAM J. Sci. and Stat. Comput., 13(5):1194-1217, 1992.","title":"New branch-and-bound rules for linear bilevel programming","authors":"Hansen","year":"1992","venue":"SIAM J. Sci. and Stat. Comput","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Jain et al., 2011] Manish Jain, Dmytro Korzhyk, Ondřej Vaněk, Vincent Conitzer, Michal Pěchouček, and Milind Tambe. A double oracle algorithm for zero-sum security games on graphs. In AAMAS, pages 327-334, 2011.","title":"A double oracle algorithm for zero-sum security games on graphs","authors":"Manish Jain, Dmytro Korzhyk, Ondřej Vaněk, Vincent Conitzer, Michal Pěchouček, Milind Tambe","year":"2011","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Junejo and Goh, 2016] Khurum Nazir Junejo and Jonathan Goh. Behaviour-based attack detection and classification in cyber physical systems using machine learning. In CPS- Sec, pages 34-43, 2016.","title":"Behaviour-based attack detection and classification in cyber physical systems using machine learning","authors":"Goh ; Junejo, Nazir Khurum, Jonathan Junejo, Goh","year":"2016","venue":"CPS-Sec","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kasiviswanathan et al., 2013] Shiva Prasad Ka- siviswanathan, Kobbi Nissim, Sofya Raskhodnikova, and Adam Smith. Analyzing graphs with node differential privacy. In Theory of Cryptography, pages 457-476.","title":"Analyzing graphs with node differential privacy","authors":"Shiva Prasad Kasiviswanathan, Kobbi Nissim, Sofya Raskhodnikova, Adam Smith","year":null,"venue":"Theory of Cryptography","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kolstad and Lasdon, 1990] Charles D Kolstad and Leon S Lasdon. Derivative evaluation and computational experi- ence with large bilevel mathematical programs. J. of opti- mization theory and applications, 65(3):485-499, 1990.","title":"Derivative evaluation and computational experience with large bilevel mathematical programs","authors":"D Charles, Leon S Kolstad, Lasdon","year":"1990","venue":"J. of optimization theory and applications","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Koufogiannis et al., 2015] Fragkiskos Koufogiannis, Shuo Han, and George J Pappas. Optimality of the laplace mech- anism in differential privacy. arXiv:1504.00065, 2015.","title":"Fragkiskos Koufogiannis","authors":"Koufogiannis","year":"2015","venue":"Optimality of the laplace mechanism in differential privacy","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2014] Chao Li, Michael Hay, Gerome Miklau, and Yue Wang. A data-and workload-aware algorithm for range queries under differential privacy. VLDB, 7(5):341- 352, 2014.","title":"A data-and workload-aware algorithm for range queries under differential privacy","authors":"Chao Li, Michael Hay, Gerome Miklau, Yue Wang","year":"2014","venue":"VLDB","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mathieu et al., 1994] R Mathieu, L Pittard, and G Anan- dalingam. Genetic algorithm based approach to bi-level linear programming. RAIRO, 28(1):1-21, 1994.","title":"Genetic algorithm based approach to bi-level linear programming","authors":"L Mathieu, G Pittard, Anandalingam","year":"1994","venue":"RAIRO","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[McSherry and Talwar, 2007] Frank McSherry and Kunal Talwar. Mechanism design via differential privacy. In FOCS, pages 94-103, 2007.","title":"Mechanism design via differential privacy","authors":"Talwar Mcsherry, Frank Mcsherry, Kunal Talwar","year":"2007","venue":"FOCS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Nguyen et al., 2016] Thanh Hong Nguyen, Arunesh Sinha, and Milind Tambe. Conquering adversary behavioral un- certainty in security games: An efficient modeling robust based algorithm. In AAAI, 2016.","title":"Conquering adversary behavioral uncertainty in security games: An efficient modeling robust based algorithm","authors":"Thanh Hong Nguyen, Arunesh Sinha, Milind Tambe","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pita et al., 2009] James Pita, Manish Jain, Fernando Ordónez, Christopher Portway, Milind Tambe, Craig Western, Praveen Paruchuri, and Sarit Kraus. Using game theory for los angeles airport security. AI magazine, 30(1):43, 2009.","title":"Using game theory for los angeles airport security","authors":"James Pita, Manish Jain, Fernando Ordónez, Christopher Portway, Milind Tambe, Craig Western, Praveen Paruchuri, Sarit Kraus","year":"2009","venue":"AI magazine","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Proserpio et al., 2014] Davide Proserpio, Sharon Goldberg, and Frank McSherry. Calibrating data to sensitivity in private data analysis: a platform for differentially-private analysis of weighted datasets. VLDB, 7(8):637-648, 2014.","title":"Calibrating data to sensitivity in private data analysis: a platform for differentially-private analysis of weighted datasets","authors":"Davide Proserpio, Sharon Goldberg, Frank Mcsherry","year":"2014","venue":"VLDB","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qardaji et al., 2014] Wahbeh Qardaji, Weining Yang, and Ninghui Li. Priview: practical differentially private release of marginal contingency tables. In ICMD, pages 1435- 1446, 2014.","title":"Priview: practical differentially private release of marginal contingency tables","authors":"Qardaji","year":"2014","venue":"ICMD","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sinha et al., 2018] Ankur Sinha, Pekka Malo, and Kalyan- moy Deb. A review on bilevel optimization: from clas- sical to evolutionary approaches and applications. IEEE Trans. on Evol. Comp., 22(2):276-295, 2018.","title":"A review on bilevel optimization: from classical to evolutionary approaches and applications","authors":"Ankur Sinha, Pekka Malo, Kalyanmoy Deb","year":"2018","venue":"IEEE Trans. on Evol. Comp","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Vicente et al., 1994] Luis Vicente, Gilles Savard, and Joaquim Júdice. Descent approaches for quadratic bilevel programming. J. of optimization theory and applications, 81(2):379-399, 1994.","title":"Descent approaches for quadratic bilevel programming","authors":"Luis Vicente, Gilles Savard, Joaquim Júdice","year":"1994","venue":"J. of optimization theory and applications","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhao et al., 2017] Mengchen Zhao, Bo An, Wei Gao, and Teng Zhang. Efficient label contamination attacks against black-box learning models. In IJCAI, pages 3945-3951, 2017.","title":"Efficient label contamination attacks against black-box learning models","authors":"Zhao","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/551"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}