Abstract
Experimentation with artificial intelligence (AI) and machine learning (ML) has rapidly advanced in the last decade, mainly due to the progress made in data storage and processing technologies. As this technology is implemented in everyday devices, ranging from smart appliances to personal assistants, we observe an increase in interest in more rigid to change sectors, like governmental and military. Utilizing a machine learning service is a commodity for today’s society, introducing data privacy challenges for data owners and security concerns for model developers. As the EU plans to build a network of AI-enabled Security Operations Centers across Europe and NATO believes in including artificial intelligence in its decision-making process, we need to focus intensely on the security and privacy offered by machine learning-based applications. This paper contains our summarization of the current concerns regarding privacy-preserving machine learning and an analysis of the present frameworks highlighting possible attacks and methodology. Additionally, we present our approach as a potential solution for privacy-preserving models used in cybersecurity applications. Our research shows that even though all three methods guarantee privacy at a certain level, a holistic approach proves to be more efficient.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Witten IH, Data mining with Weka. https://www.cs.waikato.ac.nz/ml/weka/mooc/dataminingwithweka/slides/Class5-DataMiningWithWeka-2013.pdf. Last accessed 7 Feb 2021
Rivest RL, Adleman L, Dertouzos ML (1978) On data banks and privacy homomorphisms. In: Foundation of secure computations. Academic Press, Massachusetts, United States, pp 160–179
Gentry C, A fully homomorphic encryption scheme. https://crypto.stanford.edu/craig/craig-thesis.pdf. Last accessed 7 Feb 2021
ImmuniWeb. https://www.immuniweb.com. Last accessed 6 Feb 2021
Pentoma. https://se.works/product/pentoma. Last accessed 6 Feb 2021
Wallarm platform. https://www.wallarm.com. Last accessed 6 Feb 2021
Takaesu I, Masafumi M, Yoneyama T, GyoiThon: next generation penetration test tool. https://github.com/gyoisamurai/GyoiThon. Last accessed 7 Feb 2021
Takaesu I, DeepExploit. https://github.com/13o-bbr-bbq/machine_learning_security/tree/master/DeepExploit. Last accessed 7 Feb 2021
Molloy I, Sinn M, Nicolae I, Adversarial machine learning. http://research.ibm.com/labs/ireland/nemesis2018/pdf/tutorial.pdf. Last accessed 7 Feb 2021
Al-Rubaie M, Chang JM (2018) Privacy preserving machine learning: threats and solutions. IEEE Secur Priv Mag 17(2):49–58
Kasiviswanathan S, Rudelson M, Smith A, The power of linear reconstruction attacks. https://simons.berkeley.edu/sites/default/files/docs/1119/kasiviswanathanslides.pdf. Last accessed 7 Feb 2021
Cortes C, Vapnik VN (1995) Support-vector networks. Mach Learn 20(3):273–297
Altman NS (1991) An introduction to Kernel and nearest neighbor. Am Statistic 46(3):175–185
Fredrikson M, Jha S, Ristenpart T (2015) Model inversion attacks that exploit confidence information and basic countermeasures. In: CCS ’15: proceedings of the 22nd ACM SIGSAC conference on computer and communications security. CCS 15 Conference Committee, Denver, Colorado, United States, pp 1322–1333
Tramèr F, Zhang F, Reiter MK, Ristenpart T (2016) Stealing machine learning models via prediction APIs. In: USENIX security symposium. Austin, Texas, United States
Shokri R, Stronati M, Song C, Shmatikov V (2017) Membership inference attacks against machine learning models. In: 2017 IEEE symposium on security and privacy (SP). IEEE, San Jose, California, United States
Lee W-H, Liu C, Ji S, Mittal P, Lee RB (2017) Blind de-anonymization attacks using social networks. In: WPES ‘17: proceedings of the 2017 on workshop on privacy in the electronic society. Association for Computing Machinery, New York, New York, United States, pp 1–4
Nguyen TT, Nguyen CM, Nguyen DT, Nguyen DT, Nahavandi S (2019) Deep learning for deepfakes creation and detection: a survey. Comput Vis Patt Recognit
Weinert A, Campbell S, Vela A, Schuldt D, Kurucar J (2018) Well-clear recommendation for small unmanned aircraft systems based on unmitigated collision risk. J Air Transport 26(3):113–122
Samarati P, Sweeney L (1998) Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression. Carnegie Mellon University—Journal contribution
Young A, Yung M (1996) Cryptovirology: extortion-based security threats and countermeasures. In: IEEE symposium on security and privacy. IEEE, Oakland, California, United States, pp 129–140
Gentry C (2009) Fully homomorphic encryption using ideal lattices. In: STOC ‘09: proceedings of the forty-first annual ACM symposium on theory of computing. Association for Computing Machinery, New York, New York, United States, pp 169–178
Graepel T, Lauter K, Naehrig M (2012) ML confidential: machine learning on encrypted data. In: Kwon T, Lee MK, Kwon D (eds) Information security and cryptology—ICISC 2012. ICISC 2012. Lecture notes in computer science, vol 7839. Springer, Berlin, Heidelberg
Sahai A, Waters B (2005) Fuzzy identity-based encryption. In: Cramer R (eds) Advances in cryptology—EUROCRYPT 2005. EUROCRYPT 2005. Lecture notes in computer science, vol 3494. Springer, Berlin, Heidelberg
Damgård I, Pastro V, Smart N, Zakarias S (2012) Multiparty computation from somewhat homomorphic encryption. In: Safavi-Naini R, Canetti R (eds) Advances in cryptology—CRYPTO 2012. CRYPTO 2012. Lecture notes in computer science, vol 7417. Springer, Berlin, Heidelberg
Chen V, Pastro V, Raykova M, Secure Computation for Machine Learning With SPDZ. https://arxiv.org/abs/1901.00329. Last accessed 7 Feb 2021
Dwork C, McSherry F, Nissim K, Smith A (2006) Calibrating noise to sensitivity in private data analysis. In: Halevi S, Rabin T (eds) Theory of cryptography. TCC 2006. Lecture notes in computer science, vol 3876. Springer, Berlin, Heidelberg
Papernot N, Abadi M, Erlingsson U, Goodfellow I, Talwar K, Semi-supervised Knowledge transfer for deep learning from private training data. https://arxiv.org/abs/1610.05755. Last accessed 7 Feb 2021
Tanuwidjaja HC, Choi R, Baek S, Kim K (2020) Privacy-preserving deep learning on machine learning as a service—a comprehensive survey. In: IEEE Access. IEEE, pp 167425–167447
Aristizabal A, Making PATE bidirectionally private. https://towardsdatascience.com/making-pate-bidirectionally-private-6d060f039227. Last accessed 7 Feb 2021
Mohassel P, Rindal P (2018) ABY3: a mixed protocol framework for machine learning. In: CCS ’18: proceedings of the 2018 ACM SIGSAC conference on computer and communications security. Association for Computing Machinery, New York, New York, United States, pp 35–52
NIS Directive. https://www.enisa.europa.eu/topics/nis-directive. Last accessed 7 Feb 2021
General Data Protection Regulation (GDPR). https://www.enisa.europa.eu/topics/data-protection. Last accessed 7 Feb 2021
Microsoft SEAL. https://github.com/Microsoft/SEAL. Last accessed 7 Feb 2021
Helib. https://github.com/shaih/HElib. Last accessed 7 Feb 2021
Ibarrondo A, Gomez L, Python for homomorphic encryption library. https://github.com/ibarrond/Pyfhel. Last accessed 7 Feb 2021
Chillotti I, Gama N, Georgieva M, Izabachène M (2016) Faster fully homomorphic encryption: bootstrapping in less than 0.1 seconds. In: Cheon J, Takagi T (eds) Advances in cryptology—ASIACRYPT 2016. ASIACRYPT 2016. Lecture notes in computer science, vol 10031. Springer, Berlin, Heidelberg
Ducas L, Micciancio D (2015) FHEW: bootstrapping homomorphic encryption in less than a second. In: Oswald E, Fischlin M (eds) Advances in cryptology—EUROCRYPT 2015. EUROCRYPT 2015. Lecture notes in computer science, vol 9056. Springer, Berlin, Heidelberg
TFHE: fast fully homomorphic encryption library over the Torus. https://github.com/tfhe/tfhe. Last accessed 7 Feb 2021
Chillotti I, Gama N, Georgieva M, Izabachène M (2017) Faster packed homomorphic operations and efficient circuit bootstrapping for TFHE. In: Takagi T, Peyrin T (eds) Advances in cryptology—ASIACRYPT 2017. ASIACRYPT 2017. Lecture notes in computer science, vol 10624. Springer, Cham
Dai W, Sunar B (2016) cuHE: a homomorphic encryption accelerator library. In: Pasalic E, Knudsen L (eds) Cryptography and information security in the Balkans. BalkanCryptSec 2015. Lecture notes in computer science, vol 9540. Springer, Cham
cuFHE. https://github.com/vernamlab/cuFHE. Last accessed 7 Feb 2021
NuFHE, a GPU-powered Torus FHE implementation. https://nufhe.readthedocs.io/en/latest/. Last accessed 7 Feb 2021
Slamanig D, Stingl C (2009) Investigating anonymity in group based anonymous authentication. In: Matyáš V, Fischer-Hübner S, Cvrček D, Švenda P (eds) The future of identity in the information society. Privacy and identity 2008. IFIP advances in information and communication technology, vol 298. Springer, Berlin, Heidelberg
Li L, Pal B, Ali J, Sullivan N, Chatterjee R, Ristenpart T (2019) Protocols for checking compromised credentials. In: CCS ‘19: proceedings of the 2019 ACM SIGSAC conference on computer and communications security. ACM SIGSAC, London, United Kingdom, pp 1387–1403
ssdeep—Fuzzy hashing program. https://ssdeep-project.github.io. Last accessed 7 Feb 2021
Kornblum J (2006) Identifying almost identical files using context triggered piecewise hashing. Digit Investig 3(Supplement):91–97
TFEncrypted. https://github.com/tf-encrypted/tf-encrypted. Last accessed 7 Feb 2021
NVIDIA A100 Tensor Core GPU. https://www.nvidia.com/en-us/data-center/a100/. Last accessed 2 Feb 2021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nilă, C., Preda, M., Patriciu, V. (2022). Privacy-Preserving Framework for Deep Learning Cybersecurity Solutions. In: Ciurea, C., Boja, C., Pocatilu, P., Doinea, M. (eds) Education, Research and Business Technologies. Smart Innovation, Systems and Technologies, vol 276. Springer, Singapore. https://doi.org/10.1007/978-981-16-8866-9_18
Download citation
DOI: https://doi.org/10.1007/978-981-16-8866-9_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8865-2
Online ISBN: 978-981-16-8866-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)